© 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. 10-GEMMASCOPE-RES-131K
    7. 85641
    Prev
    Next
    INDEX
    Explanations

    clarifications and proper nouns

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

    The neuron strongly activates on any occurrence of the “clar” root (as in clarify, clarification, clarifiers, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    一说
    -2.38
     sucedió
    -2.36
    囀
    -2.30
    淥
    -2.30
    𖣘
    -2.28
    賔
    -2.25
     інших
    -2.23
    хода
    -2.20
    鲻
    -2.20
    —¿
    -2.19
    POSITIVE LOGITS
    2
    3.00
    7
    2.80
    [
    2.73
    ing
    2.66
    u
    2.66
    o
    2.64
    6
    2.55
    '
    2.52
    us
    2.47
    .
    2.41
    Activations Density 0.003%

    No Known Activations