© 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. 129470
    Prev
    Next
    INDEX
    Explanations

    boolean logic and comparisons

    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
     ativos
    -0.95
    issipp
    -0.91
    hört
    -0.90
    鱿
    -0.90
     úteis
    -0.88
     pentru
    -0.87
     einzigartigen
    -0.86
     conquête
    -0.85
    cipital
    -0.85
     októ
    -0.84
    POSITIVE LOGITS
     absence
    1.19
     matematik
    1.07
     математи
    1.07
     boolean
    1.02
     we
    0.99
     brevet
    0.92
     falle
    0.92
     traged
    0.91
     contrat
    0.91
     olympique
    0.91
    Activations Density 0.004%

    No Known Activations