© 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. 16647
    Prev
    Next
    INDEX
    Explanations

    code and system commands

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

    This neuron detects programming identifiers (e.g. function or method names, API calls, and command names) in code snippets.

    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
    4
    -1.89
    8
    -1.80
    3
    -1.72
    5
    -1.71
    6
    -1.66
    9
    -1.64
    7
    -1.58
    0
    -1.55
    2
    -1.38
    ↵↵↵↵↵↵↵↵↵↵
    -1.12
    POSITIVE LOGITS
    IANGLES
    1.13
     crossorigin
    1.09
    ạng
    1.07
     effray
    1.05
    yyv
    1.03
    ⏬
    1.02
    цени
    1.02
    eada
    1.01
     煮
    0.99
    bkz
    0.99
    Activations Density 0.017%

    No Known Activations