© 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. 107109
    Prev
    Next
    INDEX
    Explanations

    code or technical terms

    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
     sometimes
    -0.88
     behauptet
    -0.81
    Sometimes
    -0.73
    namn
    -0.73
    perimeter
    -0.72
     coordenadas
    -0.70
    rdd
    -0.69
     fruta
    -0.69
    dhist
    -0.68
    ísmo
    -0.68
    POSITIVE LOGITS
     qb
    1.15
    qb
    1.12
    typeorm
    1.05
     Entity
    0.88
    OrFail
    0.81
     entity
    0.81
     Relation
    0.79
    entity
    0.78
    芭
    0.78
     Orm
    0.77
    Activations Density 0.007%

    No Known Activations