© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9699
    Prev
    Next
    INDEX
    Explanations

    seo strategy and marketing

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires strongly on named entities and other proper nouns (e.g. “Instagram,” “Wednesday,” “Tie-Break Tens,” “Jan.”) as well as capitalized pronouns, i.e. tokens marking specific names, dates, or events.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    apostrophes in contractions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    punctuation marks—especially apostrophes in contractions and semicolons—within quoted or formatted text.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Estados
    0.81
    Grim
    0.79
    Ei
    0.79
    AMC
    0.77
    ES
    0.75
    2
    0.75
    HS
    0.74
    AG
    0.73
    8
    0.73
    6
    0.72
    POSITIVE LOGITS
     emojis
    0.95
     emoji
    0.88
     microphones
    0.87
     paraphr
    0.86
     poetic
    0.85
     notepad
    0.84
     infographics
    0.84
     helpen
    0.82
     scripture
    0.81
     brainstorming
    0.81
    Activations Density 0.001%

    No Known Activations