© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13048
    Prev
    Next
    INDEX
    Explanations

    parser, lexer, consumed, Butler, Synthesis, Assad

    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
     aktor
    -1.04
    tioners
    -1.03
    oples
    -1.02
     gefe
    -1.01
     heilige
    -1.00
    forgot
    -0.98
    malte
    -0.97
    plakat
    -0.97
     другая
    -0.96
    groet
    -0.95
    POSITIVE LOGITS
     at
    1.05
     there
    0.94
     mentales
    0.90
     xứ
    0.88
     Dispenser
    0.87
    There
    0.87
     Decorations
    0.86
    мана
    0.85
     Particularly
    0.85
    гиоз
    0.84
    Activations Density 0.019%

    No Known Activations