© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108714
    Prev
    Next
    INDEX
    Explanations

    option or version

    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
     Screen
    -0.73
     static
    -0.72
     screen
    -0.71
    ุก
    -0.69
    ska
    -0.68
     SCREEN
    -0.68
     яи
    -0.67
     ответ
    -0.66
     forbidden
    -0.65
     Static
    -0.65
    POSITIVE LOGITS
    betreuung
    0.78
    LOW
    0.73
     Tiong
    0.71
    waste
    0.67
    ETH
    0.67
    みや
    0.67
    ningens
    0.66
    犸
    0.66
    Nas
    0.65
    XPath
    0.65
    Activations Density 0.070%

    No Known Activations