© 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. 32754
    Prev
    Next
    INDEX
    Explanations

    names and code components

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

    This neuron specializes in spotting programming‐language code tokens (identifiers, keywords, and syntax) rather than normal text.

    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
     onOptions
    -1.05
    不但
    -1.03
    batterie
    -1.02
    características
    -1.02
     Gibt
    -1.00
     chanh
    -0.99
     TMPro
    -0.99
     Sudah
    -0.98
    Índice
    -0.96
     nicht
    -0.96
    POSITIVE LOGITS
     process
    1.20
     what
    1.19
     filós
    1.10
    𝑞
    1.08
     sogenannten
    1.07
     Mercurio
    1.05
     memungkinkan
    1.04
    ⟼
    1.04
     escuchado
    1.00
     rijk
    0.99
    Activations Density 0.009%

    No Known Activations