© 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. 40497
    Prev
    Next
    INDEX
    Explanations

    claimant

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

    The neuron detects occurrences of the word “claimant” (or its subtoken “ant”) in legal text.

    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
    u
    -2.56
    b
    -2.38
    m
    -2.23
    。
    -2.08
    In
    -2.02
    鄚
    -2.00
    h
    -1.98
     relatifs
    -1.98
    います
    -1.95
     Worlds
    -1.95
    POSITIVE LOGITS
    ጧ
    2.75
    คนที่
    2.25
    their
    2.22
     更
    2.20
    歘
    2.16
    vée
    2.14
    无双
    2.13
    艄
    2.09
    lgari
    2.08
    vantaged
    1.98
    Activations Density 0.006%

    No Known Activations