© 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. 10-GEMMASCOPE-RES-131K
    7. 100409
    Prev
    Next
    INDEX
    Explanations

    initialization code keywords

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

    code syntax elements like colons, parentheses, and parameter separators in programming languages.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on the Objective-C “dispatch_once” singleton/one-time-initialization pattern.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     on
    -1.55
     "
    -1.43
     who
    -1.40
     -
    -1.39
     any
    -1.31
     '
    -1.30
     by
    -1.28
    љу
    -1.22
     cualquier
    -1.19
     будь
    -1.19
    POSITIVE LOGITS
    Carcinogenicity
    1.49
     tež
    1.36
     beliebt
    1.34
     teuer
    1.31
     hembra
    1.31
    laund
    1.28
    monės
    1.27
     imagenes
    1.25
     ghiaccio
    1.24
     suiker
    1.23
    Activations Density 0.065%

    No Known Activations