© 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. 34-GEMMASCOPE-RES-131K
    7. 48006
    Prev
    Next
    INDEX
    Explanations

    code includes

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

    This neuron fires on code‐structure tokens such as preprocessor markers (“#”), header‐file extensions (“.hh”), and HTML tag names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     constipation
    -0.68
    rout
    -0.66
    是这样
    -0.65
    选择的
    -0.65
     attrs
    -0.65
    贮
    -0.63
    承诺
    -0.63
     Eggers
    -0.63
    }{}
    -0.63
     scrape
    -0.61
    POSITIVE LOGITS
     KP
    0.71
    KP
    0.68
    FINAL
    0.68
     impractical
    0.67
    ūsų
    0.66
    晕
    0.66
     GOOD
    0.66
    Result
    0.65
     disqual
    0.65
    retanto
    0.64
    Activations Density 0.067%

    No Known Activations