© 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. 78672
    Prev
    Next
    INDEX
    Explanations

    code constructs and processing details

    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
    mons
    -0.89
     lakini
    -0.81
     Soy
    -0.79
     laissant
    -0.79
    uszcz
    -0.78
    NewRow
    -0.76
     թվական
    -0.76
    velt
    -0.75
     všetky
    -0.75
    licante
    -0.72
    POSITIVE LOGITS
     protect
    0.82
     protected
    0.79
    皇子
    0.79
    telde
    0.79
     protects
    0.76
    Diz
    0.74
    เคย
    0.74
    recipients
    0.69
     tracking
    0.69
     previous
    0.69
    Activations Density 0.000%

    No Known Activations