© 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. 3674
    Prev
    Next
    INDEX
    Explanations

    Struts XML configuration properties

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

    The neuron responds to mentions of programming technologies—frameworks, libraries, and related code identifiers.

    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
    Modifiers
    -0.78
    }{$\
    -0.75
    INAR
    -0.74
     آذ
    -0.74
     visco
    -0.74
     shot
    -0.73
     fornire
    -0.71
    pharm
    -0.71
     "'";
    -0.70
    rischen
    -0.70
    POSITIVE LOGITS
     Action
    0.92
     piring
    0.84
     還
    0.80
     aplik
    0.77
    RESET
    0.76
     Chaves
    0.75
    виться
    0.74
    tiles
    0.74
     consciente
    0.73
     casque
    0.73
    Activations Density 0.008%

    No Known Activations