© 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. 31-GEMMASCOPE-2-RES-16K
    7. 3058
    Prev
    Next
    INDEX
    Explanations

    all, more, and quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
     গোলাপ
    0.61
    🗯
    0.59
    🕝
    0.59
    ψει
    0.58
    🕜
    0.58
     好
    0.57
    🏤
    0.57
    ᅳ
    0.57
    🌤
    0.57
    fluoro
    0.56
    POSITIVE LOGITS
     all
    0.86
     ALL
    0.72
     All
    0.72
     все
    0.66
    所有的
    0.66
     skew
    0.63
     sunt
    0.63
    AllResult
    0.63
    All
    0.63
     arc
    0.62
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.