© 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. 39476
    Prev
    Next
    INDEX
    Explanations

    code documentation and special characters

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

    The neuron fires on documentation‐style annotation tags (e.g. @param, @return, @example) in code comments.

    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
     perna
    -1.13
     CARTOON
    -1.11
    bbling
    -1.05
     RECIPES
    -1.02
     TRAVEL
    -1.00
    providedIn
    -0.99
    >-->
    -0.97
     utensi
    -0.96
    getDate
    -0.95
     maría
    -0.95
    POSITIVE LOGITS
     adecuados
    1.02
     bustle
    0.96
     inlets
    0.89
     sandstones
    0.89
    Expl
    0.88
    ようで
    0.88
     bestaande
    0.87
     meestal
    0.86
    ignition
    0.85
    误会
    0.85
    Activations Density 0.000%

    No Known Activations