© 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. 10-GEMMASCOPE-RES-131K
    7. 113185
    Prev
    Next
    INDEX
    Explanations

    setting default properties or titles

    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
     OGSÅ
    -2.66
     
    -2.31
     them
    -2.28
     The
    -2.23
    Determining
    -2.13
     únicas
    -2.08
     harten
    -2.08
    描く
    -2.08
     geringen
    -2.05
     Otras
    -2.03
    POSITIVE LOGITS
    the
    2.77
    '
    2.30
    ’
    2.27
     komór
    2.23
     andré
    2.20
     berger
    2.20
    *
    2.19
    
    2.17
    "
    2.14
    你
    2.14
    Activations Density 0.000%

    No Known Activations