© 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. 38991
    Prev
    Next
    INDEX
    Explanations

    programming setup actions

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

    The neuron activates on programming identifiers for functions or methods (e.g. “init,” “validate,” “update,” “draw,” “fill”).

    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
     sachsen
    -1.05
    aussi
    -1.04
    dosen
    -1.01
     evolução
    -1.00
     čaj
    -1.00
    たつ
    -0.99
     discussão
    -0.99
     intenção
    -0.96
     redaktion
    -0.95
     kleid
    -0.94
    POSITIVE LOGITS
    ();
    1.30
    ();
    1.09
     first
    1.08
    gantes
    1.00
     makes
    0.99
     low
    0.98
    !
    0.97
     will
    0.95
     making
    0.95
     choose
    0.95
    Activations Density 0.010%

    No Known Activations