© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 128572
    Prev
    Next
    INDEX
    Explanations

    PHP code snippets and comments

    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_10/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
     to
    -2.13
    )):
    
    -1.38
    ));
    
    -1.38
    ными
    -1.32
    ным
    -1.30
     in
    -1.29
    .,"
    -1.29
     "-
    -1.27
     $\
    -1.27
     \
    -1.27
    POSITIVE LOGITS
    のおかげ
    1.52
    This
    1.52
    Dette
    1.36
    由於
    1.34
    mejores
    1.33
     داشتم
    1.31
     azienda
    1.30
     Asking
    1.30
    activar
    1.30
    .
    1.29
    Activations Density 0.017%

    No Known Activations