© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108034
    Prev
    Next
    INDEX
    Explanations

    criminal use/trespass/damaging

    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
    的行为
    -0.77
    ulement
    -0.77
    álat
    -0.73
    cleaned
    -0.71
     acquitted
    -0.69
    uctura
    -0.69
     Humanity
    -0.67
    æs
    -0.67
    cangan
    -0.67
     aplikacji
    -0.66
    POSITIVE LOGITS
    Script
    0.75
    ToDouble
    0.69
    unary
    0.64
    FAMILY
    0.62
     impres
    0.61
     Rio
    0.61
    ioon
    0.61
    Gate
    0.60
    シン
    0.60
    issen
    0.59
    Activations Density 0.090%

    No Known Activations