© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 24928
    Prev
    Next
    INDEX
    Explanations

    [numeric identifier]

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

    This neuron detects numeric reference or citation identifiers in academic-style bracketed or tagged citations.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     of
    -1.63
     to
    -1.55
     as
    -1.48
     for
    -1.36
     after
    -1.31
     other
    -1.13
     before
    -1.09
     along
    -1.05
     while
    -1.05
     also
    -1.05
    POSITIVE LOGITS
    Rumah
    1.16
    ᥫ
    1.13
    زندگی
    1.13
    今天
    1.12
    uary
    1.12
    ätt
    1.11
    venser
    1.11
    actoring
    1.10
    acterium
    1.10
     peluche
    1.10
    Activations Density 0.051%

    No Known Activations