© 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. 10-GEMMASCOPE-RES-131K
    7. 41930
    Prev
    Next
    INDEX
    Explanations

    claim preclusion

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

    The neuron detects occurrences of the standalone word “claim” (as used in legal, patent, or discussion contexts).

    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
    and
    -3.61
     -
    -3.25
    Previously
    -3.09
     и
    -3.08
    Although
    -2.97
    ременно
    -2.91
    Only
    -2.88
    Some
    -2.86
    One
    -2.84
    While
    -2.78
    POSITIVE LOGITS
    韡
    3.22
    詎
    3.17
    er
    3.14
    黉
    2.95
    ophageal
    2.95
    餍
    2.92
    圌
    2.86
    阏
    2.84
     интервью
    2.84
    ſam
    2.84
    Activations Density 0.005%

    No Known Activations