© 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. 34-GEMMASCOPE-RES-131K
    4. 79453
    Prev
    Next
    INDEX
    Explanations

    Austin, Texas LICENSE

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

    The neuron is keyed to numeric tokens—especially dates, docket numbers, and other number‐like strings.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     and
    -2.61
     for
    -2.52
     from
    -2.42
     with
    -2.33
     gives
    -2.20
     after
    -2.20
     first
    -2.11
     had
    -2.06
     on
    -2.05
     without
    -2.05
    POSITIVE LOGITS
     shimmering
    2.03
     astounding
    1.91
     ridiculously
    1.91
     ジップ
    1.90
     insanely
    1.88
    commonly
    1.88
     luscious
    1.87
     ludicrous
    1.86
     wacky
    1.85
    aning
    1.84
    Activations Density 0.008%

    No Known Activations