© 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. 129856
    Prev
    Next
    INDEX
    Explanations

    the neuron detects identifiers used as the left‐hand side of assignment statements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    assign or compare

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ↛
    -0.95
    zijn
    -0.93
    amid
    -0.91
     minimalista
    -0.90
    Again
    -0.90
    again
    -0.89
    Pontos
    -0.88
    很重要
    -0.86
    杳
    -0.86
    amentul
    -0.86
    POSITIVE LOGITS
    ner
    0.99
     only
    0.96
     =
    0.91
    helm
    0.89
    šanās
    0.88
    ????
    0.87
    ton
    0.85
     nearly
    0.81
     more
    0.81
    Interment
    0.80
    Activations Density 0.003%

    No Known Activations