© 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. 63128
    Prev
    Next
    INDEX
    Explanations

    license text and path separators

    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
    爱
    -0.73
    Гор
    -0.71
    Control
    -0.70
    Bor
    -0.69
    Body
    -0.68
    最大
    -0.68
     Gill
    -0.67
    Test
    -0.66
    tell
    -0.66
     telling
    -0.66
    POSITIVE LOGITS
     frü
    0.75
    Perd
    0.75
    convenience
    0.75
    dataArray
    0.71
     протяжении
    0.70
     provoca
    0.70
    particularly
    0.69
     AÑO
    0.69
    idf
    0.68
    strategies
    0.68
    Activations Density 0.054%

    No Known Activations