© 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. 10-GEMMASCOPE-RES-131K
    7. 73908
    Prev
    Next
    INDEX
    Explanations

    dates with months

    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_10/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
    9
    -1.80
    2
    -1.70
    8
    -1.69
    This
    -1.68
     не
    -1.64
    When
    -1.60
    Not
    -1.59
    Get
    -1.57
     this
    -1.56
     also
    -1.53
    POSITIVE LOGITS
    
    1.73
     rése
    1.71
    鼯
    1.61
    +++++
    1.59
    罍
    1.55
     bré
    1.55
    exits
    1.52
    莇
    1.51
     peruan
    1.48
    ▍
    1.48
    Activations Density 0.212%

    No Known Activations