© 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. 79335
    Prev
    Next
    INDEX
    Explanations

    Larry Bar

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

    This neuron detects the decorative comment‐block delimiters and header annotations (e.g. rows of “*” and “@file,” “@author,” “version,” etc.) commonly used in source‐code documentation.

    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
     echter
    -0.82
     crédit
    -0.79
     Historie
    -0.76
     accueil
    -0.73
     Harus
    -0.71
    礡
    -0.71
     Méndez
    -0.71
     antik
    -0.71
     tarik
    -0.71
    clientId
    -0.70
    POSITIVE LOGITS
     HAL
    1.18
     BSP
    1.08
    TypeDef
    1.08
    BSP
    1.00
    HAL
    1.00
    TIM
    0.88
     TIM
    0.86
     USGS
    0.84
    ælde
    0.84
     Sept
    0.81
    Activations Density 0.023%

    No Known Activations