© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68490
    Prev
    Next
    INDEX
    Explanations

    interval or scene

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

    The neuron strongly activates on CJK tokens containing the character “間” (as in words for interval, time duration, or within a range).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    塤
    -2.72
    躥
    -2.61
     besseren
    -2.61
    </b>
    -2.58
    佮
    -2.56
    妺
    -2.53
    闋
    -2.48
    顰
    -2.47
    〼
    -2.44
    をご
    -2.42
    POSITIVE LOGITS
    y
    3.97
    as
    3.44
    -
    3.22
    O
    3.20
    G
    3.14
    at
    3.14
    U
    3.03
    C
    3.00
    r
    2.97
    3
    2.91
    Activations Density 0.001%

    No Known Activations