© 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. 22-GEMMASCOPE-RES-131K
    7. 64457
    Prev
    Next
    INDEX
    Explanations

    // Jest snapshot code

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

    The neuron strongly activates on the digit “0” (especially when it appears in URLs or percent‐encoded sequences).

    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
    が無い
    -1.43
     dîner
    -1.37
     organisme
    -1.31
     Hrvats
    -1.22
     espir
    -1.20
    ＝＝＝＝
    -1.19
    　“
    -1.18
     sabah
    -1.18
     photographe
    -1.16
    wurde
    -1.16
    POSITIVE LOGITS
    in
    1.27
     now
    1.20
    )
    1.18
     nuevamente
    1.18
     string
    1.15
    --
    1.14
     soprattutto
    1.14
    —
    1.12
    之所
    1.12
    i
    1.11
    Activations Density 0.000%

    No Known Activations