© 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. 34-GEMMASCOPE-RES-131K
    7. 62421
    Prev
    Next
    INDEX
    Explanations

    configuration cascade

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

    The neuron fires on tokens containing digits—i.e. numeric constants, version numbers, years, ports, log‐level values, etc.

    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
     мно
    -0.69
     jaringan
    -0.65
    antana
    -0.64
    xv
    -0.64
     نادي
    -0.63
     перевоз
    -0.63
     پارچه
    -0.63
    🦯
    -0.63
    rpg
    -0.62
     producción
    -0.61
    POSITIVE LOGITS
     Champs
    0.75
    quête
    0.72
    level
    0.71
     Astra
    0.71
    fizierung
    0.70
    Kepala
    0.69
    ﾆ
    0.68
     Champ
    0.67
    gula
    0.67
     خوبه
    0.66
    Activations Density 0.067%

    No Known Activations