© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6228
    Prev
    Next
    INDEX
    Explanations

    ```csharpprogram structure

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

    The neuron fires on words that appear in document section headers or titles (e.g. the “When is…”, “No. 48626 Supreme Court of Nevada,” “Appeal,” “Porter’s,” “SWOT,” etc.).

    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
    ২
    0.86
    ı
    0.81
    吗
    0.75
    ă
    0.73
    ご覧
    0.71
    郸
    0.70
    и
    0.70
    ৩
    0.70
     Maulana
    0.69
    ї
    0.69
    POSITIVE LOGITS
    ERON
    0.87
     MeOH
    0.83
     capazes
    0.82
    Multiplier
    0.81
    RESET
    0.80
    RANGE
    0.80
    此之外
    0.80
    IONS
    0.79
    ERK
    0.79
     serre
    0.79
    Activations Density 0.000%

    No Known Activations