© 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. 25109
    Prev
    Next
    INDEX
    Explanations

    programming identifiers and properties

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

    the neuron activates on programming identifiers (variable, function, or property names) in code.

    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
     作り方
    -1.56
     fonde
    -1.35
    familie
    -1.33
     emblema
    -1.30
    หรือ
    -1.30
    wär
    -1.27
    tellers
    -1.26
    Beskrivning
    -1.26
     maje
    -1.25
     radikal
    -1.25
    POSITIVE LOGITS
    _
    1.32
    T
    1.27
    M
    1.25
    P
    1.24
    H
    1.23
    F
    1.20
    G
    1.18
    因为它
    1.17
     Ответить
    1.16
    R
    1.16
    Activations Density 0.014%

    No Known Activations