© 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. 73470
    Prev
    Next
    INDEX
    Explanations

    list structures and punctuation

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

    This neuron fires on the first item in literal lists or array initializers.

    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
     by
    -1.28
    ”,
    -1.26
    providedIn
    -1.14
     of
    -1.03
    する
    -1.02
     with
    -1.02
    ’,
    -1.02
    nextProps
    -1.00
    пон
    -1.00
     still
    -1.00
    POSITIVE LOGITS
    Stap
    1.19
     ventajas
    1.18
    enggarakan
    1.16
     labores
    1.16
    Hacer
    1.13
    hacer
    1.13
     evaluaciones
    1.11
     prisa
    1.11
    Dá
    1.09
    
    1.09
    Activations Density 0.017%

    No Known Activations