© 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. 12373
    Prev
    Next
    INDEX
    Explanations

    Choose whichever

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

    The neuron flags emphatic promotional or call-to-action cues—especially exclamation marks and imperative marketing language.

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

    closing quotation marks in promotional or instructional text.

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

    upbeat promotional or call-to-action language typical of marketing and customer communications.

    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
    ک
    0.82
    ری
    0.80
     Ê
    0.77
    لا
    0.76
    ق
    0.76
     πρώ
    0.74
    کي
    0.73
    ﮑ
    0.73
    یه
    0.72
     刘
    0.71
    POSITIVE LOGITS
    NG
    0.83
    вары
    0.82
    ОР
    0.80
    льности
    0.80
    মিক্যাল
    0.79
     competitor
    0.78
    лад
    0.77
    IO
    0.76
    hotel
    0.75
    вате
    0.75
    Activations Density 0.000%

    No Known Activations