© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38762
    Prev
    Next
    INDEX
    Explanations

    section titles

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

    The neuron fires on metadata in code/docs—especially version numbers and license/file‐reference 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_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
     måneder
    -1.17
     tartış
    -1.07
     aldri
    -1.05
     gjen
    -1.02
     herz
    -1.02
    龵
    -1.00
     måte
    -0.99
     türkiye
    -0.98
     overras
    -0.98
     manque
    -0.98
    POSITIVE LOGITS
    一番
    0.96
    mathrm
    0.94
     другие
    0.91
     avantaj
    0.90
     liegenden
    0.90
    er
    0.88
    стно
    0.88
        
    0.88
    表示
    0.86
    wiegend
    0.85
    Activations Density 0.000%

    No Known Activations