© 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. 31030
    Prev
    Next
    INDEX
    Explanations

    web content and URLs

    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
    -0.89
     alba
    -0.89
    -0.88
     prezent
    -0.82
     lampe
    -0.81
    setProgress
    -0.81
     veja
    -0.77
    ческой
    -0.77
     retourner
    -0.77
     anivers
    -0.75
    POSITIVE LOGITS
    Rc
    0.81
    :=\
    0.78
    枸
    0.73
    CFLAGS
    0.73
     Piece
    0.71
     country
    0.71
     prič
    0.71
    tari
    0.70
    pagnol
    0.70
     sobie
    0.70
    Activations Density 0.001%

    No Known Activations