© 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. 84476
    Prev
    Next
    INDEX
    Explanations

    java class names

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

    This neuron spotlights code identifiers consisting of uppercase or CamelCase names, i.e. class, type, or constant names in import statements.

    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
    虽说
    -1.32
    Preparazione
    -1.27
     作り方
    -1.16
    Gruppo
    -1.10
    équipements
    -1.09
    Trama
    -1.09
    不可思议
    -1.08
     immeasurable
    -1.07
    Procedimento
    -1.07
    Geral
    -1.06
    POSITIVE LOGITS
     dergleichen
    1.41
     that
    1.34
     how
    1.33
    ;
    1.30
    ;
    1.27
     able
    1.21
     them
    1.20
    不正
    1.17
    as
    1.13
    НОЕ
    1.08
    Activations Density 0.029%

    No Known Activations