© 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. 22-GEMMASCOPE-RES-131K
    7. 72324
    Prev
    Next
    INDEX
    Explanations

    static declarations

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

    This neuron fires on occurrences of the keyword “static” (i.e. static declarations).

    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
     also
    -1.10
     they
    -1.03
    iferous
    -1.02
    OrUpdate
    -1.01
    儚
    -0.99
    Válasz
    -0.98
     soprattutto
    -0.96
     dépenses
    -0.96
     EVEN
    -0.96
    鰹
    -0.95
    POSITIVE LOGITS
    conceito
    1.05
     water
    0.91
     traits
    0.90
     volumes
    0.89
    coes
    0.89
     with
    0.89
     behaviors
    0.89
    userRepository
    0.89
     Thebes
    0.88
    $};
    0.88
    Activations Density 0.003%

    No Known Activations