© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 10538
    Prev
    Next
    INDEX
    Explanations

    technical programming nouns

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

    class names and object types in programming code, particularly capitalized identifiers that represent classes, modules, or namespaces.

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

    This neuron detects PascalCase identifiers, especially class and namespace names in code.

    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
     and
    -2.17
     Both
    -1.43
     Botschaft
    -1.34
     Kampagne
    -1.31
     ("
    -1.26
     in
    -1.24
     that
    -1.22
    ↵↵
    -1.21
     with
    -1.21
     \
    -1.18
    POSITIVE LOGITS
     généralement
    1.34
    ⢫
    1.34
     recente
    1.32
     enfe
    1.30
     mercato
    1.30
    扨
    1.27
     quoique
    1.27
     ジップ
    1.26
    doesn
    1.25
     autunno
    1.25
    Activations Density 0.119%

    No Known Activations