© 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. 93211
    Prev
    Next
    INDEX
    Explanations

    `[Required]` attribute and code

    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
    鹫
    -0.80
     killing
    -0.77
    лизм
    -0.74
    Killing
    -0.72
    $_(
    -0.71
    ائمة
    -0.71
    ופן
    -0.71
    酉
    -0.70
    remacy
    -0.70
    平安
    -0.70
    POSITIVE LOGITS
     Display
    1.24
    Display
    1.16
     display
    0.95
     RANGE
    0.88
     Remote
    0.86
    display
    0.86
    DataType
    0.84
    cshtml
    0.84
    DISPLAY
    0.84
     DISPLAY
    0.83
    Activations Density 0.005%

    No Known Activations