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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8747
    Prev
    Next
    INDEX
    Explanations

    assets, using, growing, related, quickly, Selenium

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

    The neuron is primarily responding to content‐bearing “content words” (mostly nouns, pronouns, and technical terms) rather than to purely grammatical or function words.

    oai_token-act-pair · o4-miniTriggered 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
    প
    0.89
    पुरम
    0.78
    et
    0.77
    ారి
    0.76
    фт
    0.75
    n
    0.75
    дован
    0.74
    plats
    0.73
    قم
    0.71
    en
    0.71
    POSITIVE LOGITS
     Salts
    0.83
     Dritt
    0.78
    
    0.78
     Selenium
    0.77
     surfactants
    0.77
    தில்
    0.74
     Perk
    0.73
    HLA
    0.72
    )—
    0.72
     Patio
    0.71
    Activations Density 0.000%

    No Known Activations