© 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. 22-GEMMASCOPE-RES-131K
    7. 73264
    Prev
    Next
    INDEX
    Explanations

    programming keywords

    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_22/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
    gangen
    -1.08
    耵
    -1.05
    strick
    -1.02
     práce
    -0.99
     getrock
    -0.96
    ண்டும்
    -0.94
    indere
    -0.92
    IBLIO
    -0.91
    tilizers
    -0.91
     virtuelle
    -0.91
    POSITIVE LOGITS
     no
    1.08
     only
    1.02
     as
    0.97
     null
    0.95
     none
    0.92
     so
    0.91
     simply
    0.91
    ...?
    0.90
    -
    0.86
     नहीं
    0.86
    Activations Density 0.006%

    No Known Activations