© 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. 34-GEMMASCOPE-RES-131K
    7. 63836
    Prev
    Next
    INDEX
    Explanations

    dedicated_ file paths

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

    This neuron fires on programming‐style tokens—identifiers, namespace or file‐path components, punctuation, and other code elements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    amore
    -0.71
     zwyk
    -0.69
     wala
    -0.69
     successes
    -0.67
     tries
    -0.66
    ねぇ
    -0.65
    ordeel
    -0.65
    ordinaire
    -0.65
    loggers
    -0.64
     Reserv
    -0.64
    POSITIVE LOGITS
     planet
    0.93
     planetary
    0.85
    了一个
    0.83
     discoveries
    0.82
     chir
    0.80
    Proced
    0.78
    Воспита
    0.78
     oxide
    0.77
     survival
    0.76
     astronaut
    0.75
    Activations Density 0.006%

    No Known Activations