© 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. 45425
    Prev
    Next
    INDEX
    Explanations

    byte sequences and numbers

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

    This neuron detects numeric code‐point sequences (e.g. the digits in “\033” or “\u0043”) used in escape or Unicode‐literal constructions.

    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
    extAlignment
    -1.35
    女
    -1.34
     老人
    -1.34
     ilişk
    -1.34
    ↵↵
    -1.33
     hacían
    -1.31
     我们
    -1.25
     动物
    -1.24
     malheure
    -1.23
    konos
    -1.19
    POSITIVE LOGITS
     babak
    1.44
     championnat
    1.27
     Cualquier
    1.27
    也在
    1.16
     SIST
    1.16
    ٦
    1.16
     diminutive
    1.16
     Aún
    1.14
    ontale
    1.12
    produces
    1.11
    Activations Density 0.030%

    No Known Activations