© 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. 90451
    Prev
    Next
    INDEX
    Explanations

    fields

    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
    essica
    -0.75
    bals
    -0.75
    ^@
    -0.75
    asai
    -0.74
    kras
    -0.74
    rilis
    -0.73
    ピュ
    -0.73
    utto
    -0.73
    alions
    -0.72
    scars
    -0.71
    POSITIVE LOGITS
    field
    1.03
     field
    0.89
    formatter
    0.83
    FIELD
    0.82
    Yas
    0.80
     Field
    0.79
     FIELD
    0.78
     revision
    0.77
    Field
    0.76
    delta
    0.75
    Activations Density 0.043%

    No Known Activations