© 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. 128478
    Prev
    Next
    INDEX
    Explanations

    transforming into simpler forms

    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
     comunque
    -0.86
     graduación
    -0.80
     école
    -0.80
     navideña
    -0.79
     ajoute
    -0.76
    rero
    -0.75
    合わない
    -0.75
     manque
    -0.75
     CORON
    -0.74
     addition
    -0.73
    POSITIVE LOGITS
     then
    1.24
     now
    1.22
     easier
    0.99
     simpler
    0.98
     dabar
    0.95
    ános
    0.91
     Uniwers
    0.90
     Mayıs
    0.90
    ebab
    0.89
    gląda
    0.89
    Activations Density 0.060%

    No Known Activations