© 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. 31259
    Prev
    Next
    INDEX
    Explanations

    event handling in 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
     المس
    -0.90
    ــــ
    -0.84
     primeiro
    -0.84
    tude
    -0.82
    などが
    -0.79
    よりは
    -0.79
    uves
    -0.79
    roxene
    -0.77
     圆
    -0.77
     πρώ
    -0.75
    POSITIVE LOGITS
     changed
    1.50
     changes
    1.43
     change
    1.33
    handleChange
    1.31
     onChange
    1.27
     changing
    1.20
    Changed
    1.16
     handleChange
    1.16
    ChangeEvent
    1.11
    onChange
    1.10
    Activations Density 0.003%

    No Known Activations