© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58013
    Prev
    Next
    INDEX
    Explanations

    `__` or path related tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    の説明
    -0.71
    CFLAGS
    -0.68
     vị
    -0.65
    ंब
    -0.65
    の山
    -0.63
    Watt
    -0.63
    ;">
    -0.63
    封闭
    -0.62
     प्रद
    -0.62
    DBMS
    -0.61
    POSITIVE LOGITS
    __
    4.50
     __
    4.22
    ________________
    3.30
    (__
    2.78
    .__
    2.77
     (__
    2.66
     "__
    2.33
    __;
    2.30
     '__
    2.27
    \_\_
    2.22
    Activations Density 0.191%

    No Known Activations