© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 7157
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
     HEX
    2.93
     hex
    2.91
     SCD
    2.84
    TypeDef
    2.80
     hexa
    2.70
    ᴙ
    2.69
     괴
    2.68
     astrocyte
    2.68
     Saturn
    2.68
     doodle
    2.67
    POSITIVE LOGITS
    حظ
    1.01
    .
    1.00
    靭
    0.99
    时间内
    0.97
    itorio
    0.97
    erdings
    0.96
    させて頂
    0.94
    ’
    0.89
    знача
    0.87
    {
    0.85
    Activations Density 0.000%

    No Known Activations