© 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. 25462
    Prev
    Next
    INDEX
    Explanations

    non-english words and code

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

    The neuron fires on identifiers used as parameter names in function or constructor signatures.

    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
     where
    -1.19
     wichtigen
    -1.03
     this
    -0.99
     it
    -0.96
     first
    -0.96
     tvar
    -0.96
     wichtige
    -0.92
    bedded
    -0.91
     if
    -0.90
     currently
    -0.90
    POSITIVE LOGITS
     médicaments
    1.07
     vrais
    1.05
     България
    1.03
     milhares
    0.99
     réinitial
    0.98
    Fonction
    0.97
     disponibilités
    0.95
     délais
    0.95
     coû
    0.94
     dépens
    0.93
    Activations Density 0.002%

    No Known Activations