© 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. 116678
    Prev
    Next
    INDEX
    Explanations

    manager or policeman

    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
    Bach
    -0.71
    DBObject
    -0.69
    井
    -0.65
     Bach
    -0.65
     kila
    -0.64
     líquidos
    -0.63
    lossenen
    -0.63
    པ་
    -0.63
    Reviews
    -0.63
     attributes
    -0.63
    POSITIVE LOGITS
     đạo
    0.79
    noks
    0.73
    assurer
    0.71
    āju
    0.71
     rowspan
    0.70
    ้าว
    0.69
    醤
    0.68
     assurer
    0.68
     keeper
    0.68
     Mauricio
    0.68
    Activations Density 0.027%

    No Known Activations