© 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. 109636
    Prev
    Next
    INDEX
    Explanations

    United States, Deputy Speaker

    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
     grader
    -0.74
     solder
    -0.73
    gnu
    -0.71
    gnum
    -0.71
    yii
    -0.69
     enamel
    -0.69
    FV
    -0.68
     reuse
    -0.67
    GN
    -0.66
    leve
    -0.66
    POSITIVE LOGITS
     chan
    0.78
    chan
    0.77
    ่ะ
    0.74
    channel
    0.73
    LORE
    0.72
    WHERE
    0.71
    Anyway
    0.71
     SET
    0.69
    Private
    0.68
    Ratio
    0.68
    Activations Density 0.042%

    No Known Activations