© 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. 100572
    Prev
    Next
    INDEX
    Explanations

    powder, powdered, powder room, powder coated

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

    The neuron detects occurrences of “powder” and related forms (e.g., “powder,” “powdered,” “wd/po‐wd‐ers”).

    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
    B
    -2.67
    R
    -2.61
    (
    -2.61
    V
    -2.59
    T
    -2.55
    in
    -2.52
    [
    -2.42
    U
    -2.39
    or
    -2.38
    ).
    -2.38
    POSITIVE LOGITS
    他们是
    2.53
    𖣔
    2.38
    meteries
    2.36
    縺
    2.30
    莇
    2.16
    蟶
    2.14
    ⑉
    2.11
     kompati
    2.09
     内衣
    2.08
    齮
    2.08
    Activations Density 0.007%

    No Known Activations