© 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. 100182
    Prev
    Next
    INDEX
    Explanations

    hellhell boyhell pizzahell on earthhell's kitchenhell not hallelujahhell on wheelshell if i couldhell is other people

    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
    juries
    -2.88
    埽
    -2.69
    entown
    -2.67
    poptotic
    -2.63
    ressee
    -2.58
    来看看
    -2.55
    圌
    -2.53
    ditionally
    -2.53
    vocations
    -2.53
    esthetics
    -2.50
    POSITIVE LOGITS
    -
    3.77
     
    3.42
    The
    2.88
     crux
    2.81
    ↵
    2.80
    <
    2.66
    That
    2.64
    2
    2.58
    ).
    2.56
    .
    2.56
    Activations Density 0.005%

    No Known Activations