© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107815
    Prev
    Next
    INDEX
    Explanations

    album, movie, secretary titles

    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
     seventies
    -0.88
     sacerdote
    -0.76
     odp
    -0.75
     efectivo
    -0.73
     desapare
    -0.71
    ällningar
    -0.71
     lenta
    -0.69
     Konkur
    -0.67
    Breaker
    -0.67
    resent
    -0.66
    POSITIVE LOGITS
    arel
    0.83
    quity
    0.75
    REV
    0.75
     Além
    0.72
    Elec
    0.71
     Bhopal
    0.71
     Chernobyl
    0.70
     RemoteException
    0.70
     Rink
    0.70
    setzer
    0.69
    Activations Density 0.099%

    No Known Activations