© 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. 63165
    Prev
    Next
    INDEX
    Explanations

    .hpp .c .h

    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
    voort
    -0.72
    cras
    -0.70
    ừng
    -0.69
    eated
    -0.69
    xsi
    -0.68
     reign
    -0.68
    punct
    -0.68
     tratto
    -0.67
     mempertahankan
    -0.67
    laway
    -0.66
    POSITIVE LOGITS
     szkol
    0.77
    extField
    0.73
     Icon
    0.73
    Multiline
    0.73
    querque
    0.73
    HSP
    0.71
    Verbose
    0.68
    ochet
    0.68
    髅
    0.67
    ceptibility
    0.67
    Activations Density 0.023%

    No Known Activations