© 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. 129761
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on code identifiers—especially multi‐letter CamelCase or capitalized names used for functions, tests, classes, or other symbols.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    code function names

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    oweit
    -1.34
     AMAZING
    -1.34
     FUCKING
    -1.31
     astounding
    -1.30
    Educación
    -1.24
     Parece
    -1.22
    手臂
    -1.22
     arrog
    -1.21
     BEAUTIFUL
    -1.19
     arrogant
    -1.18
    POSITIVE LOGITS
     with
    2.09
     on
    1.95
     not
    1.80
     from
    1.75
     as
    1.72
     without
    1.70
     by
    1.64
     no
    1.63
     after
    1.59
     to
    1.53
    Activations Density 0.014%

    No Known Activations