© 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. 73337
    Prev
    Next
    INDEX
    Explanations

    translated text and programming 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_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
    hiva
    -1.01
    ToMany
    -1.00
     eventful
    -0.97
     raça
    -0.94
    
    -0.93
     evolução
    -0.93
    gusted
    -0.91
    рует
    -0.88
    helf
    -0.88
     schild
    -0.88
    POSITIVE LOGITS
    面積
    0.97
     other
    0.96
     primero
    0.95
     hastal
    0.93
     fewer
    0.93
    Recept
    0.93
    Hilsen
    0.92
     ardent
    0.91
     więks
    0.91
     Removes
    0.91
    Activations Density 0.003%

    No Known Activations