© 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. 34-GEMMASCOPE-RES-131K
    7. 99266
    Prev
    Next
    INDEX
    Explanations

    questions and explanations

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

    The neuron specializes in spotting the “contributor license agreements.” phrase (and its surrounding punctuation) in Apache‐style license headers.

    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
    criminate
    -0.96
    Trước
    -0.96
     bombar
    -0.88
    Filmografia
    -0.85
    Werdegang
    -0.85
    ﾂ
    -0.84
     Mitter
    -0.84
    brainly
    -0.84
     estacion
    -0.83
     koje
    -0.82
    POSITIVE LOGITS
    可能有
    0.88
    íu
    0.83
     giovane
    0.79
     meistens
    0.78
     vieles
    0.77
     generan
    0.76
    大致
    0.75
     zodat
    0.74
    往往
    0.73
     facsimile
    0.73
    Activations Density 0.006%

    No Known Activations