© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127612
    Prev
    Next
    INDEX
    Explanations

    Wildcats and Bulldogs

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires almost exclusively on numeric literals (integer or decimal tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    }
    -2.33
     inextrica
    -2.27
     wavering
    -2.17
    "
    -2.17
    เวลา
    -2.03
     '
    -2.02
     права
    -2.00
     Intu
    -1.99
    }$
    -1.92
     insanların
    -1.92
    POSITIVE LOGITS
    髡
    2.84
    蕺
    2.70
    
    2.66
    雠
    2.63
    𓋼
    2.61
    砗
    2.61
    趼
    2.61
    鈊
    2.59
    詒
    2.58
    嚶
    2.42
    Activations Density 0.000%

    No Known Activations