© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68582
    Prev
    Next
    INDEX
    Explanations

    dystrophic, dyadic, dyne

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

    This neuron fires on short variable names denoting coordinate or motion deltas (e.g. dx, dy, Dz) in code.

    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
    呖
    -3.13
    嵛
    -3.11
    งิน
    -2.77
    瓩
    -2.70
     zahlreichen
    -2.66
     solchen
    -2.63
     gleichen
    -2.61
    that
    -2.56
    ほか
    -2.53
    ੝
    -2.53
    POSITIVE LOGITS
    \
    2.73
    🌻
    2.55
    ’
    2.50
    *
    2.38
     and
    2.36
     rite
    2.30
    <
    2.30
    '.'
    2.25
     januari
    2.19
     setembro
    2.17
    Activations Density 0.017%

    No Known Activations