© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2971
    Prev
    Next
    INDEX
    Explanations

    draw() function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    -
    2.61
    İ
    2.27
    '
    2.27
    ’
    1.96
    I
    1.86
    B
    1.81
    En
    1.80
    K
    1.79
    As
    1.74
    fed
    1.73
    POSITIVE LOGITS
     其
    2.99
     紅
    2.91
     ခ
    2.88
     哦
    2.84
     椅
    2.82
     資
    2.78
     ନ
    2.75
     ଜ
    2.71
     除
    2.71
     餐
    2.71
    Activations Density 0.022%

    No Known Activations