© 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. 79097
    Prev
    Next
    INDEX
    Explanations

    list properties

    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
     farby
    -0.79
     Yankee
    -0.78
    dene
    -0.77
     lignin
    -0.76
    phology
    -0.76
    sean
    -0.75
    atangan
    -0.75
    Tt
    -0.74
    addFlags
    -0.74
    zä
    -0.73
    POSITIVE LOGITS
    ток
    0.74
    arom
    0.70
     اليوم
    0.70
     ток
    0.68
     Refunds
    0.67
     misread
    0.67
    Carn
    0.67
    Numero
    0.67
    entity
    0.66
    Hak
    0.66
    Activations Density 0.008%

    No Known Activations