© 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. 3471
    Prev
    Next
    INDEX
    Explanations

    is prefix

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

    This neuron detects capitalized identifier tokens—typically programming types, constructors, or class names.

    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
    certainty
    -0.79
    Dias
    -0.79
     plantas
    -0.77
     Masyarakat
    -0.77
     one
    -0.77
     Vä
    -0.77
    nations
    -0.76
     mogelijkheden
    -0.76
     it
    -0.75
     much
    -0.75
    POSITIVE LOGITS
    bietern
    1.02
    äinen
    0.93
    ulated
    0.93
    鼓励
    0.93
     даже
    0.91
     حتی
    0.91
    OrWhiteSpace
    0.89
    ulating
    0.88
    omorphic
    0.88
    rabh
    0.87
    Activations Density 0.032%

    No Known Activations