© 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. 10-GEMMASCOPE-RES-131K
    7. 73652
    Prev
    Next
    INDEX
    Explanations

    string manipulation functions

    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
     Hinsicht
    -2.08
     if
    -2.05
    $
    -1.90
     or
    -1.76
     improve
    -1.74
     الحالي
    -1.70
    ,
    -1.70
    Since
    -1.63
     This
    -1.62
     But
    -1.59
    POSITIVE LOGITS
    癭
    2.19
    蓐
    1.96
    ‒
    1.96
    ]."
    1.94
    坶
    1.92
    "'
    1.91
    嗵
    1.90
    
    1.87
     soooo
    1.86
    ---->
    1.83
    Activations Density 0.001%

    No Known Activations