© 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. 16601
    Prev
    Next
    INDEX
    Explanations

    loop counter `i` followed by `++`

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

    The neuron detects the loop‐control increment (“i++”) in for-loop headers.

    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
     mereka
    -1.53
    matische
    -1.43
     desde
    -1.33
    开始
    -1.17
     también
    -1.17
     Vielleicht
    -1.15
    matisch
    -1.14
     from
    -1.14
     acidente
    -1.12
     drá
    -1.11
    POSITIVE LOGITS
     ALLE
    1.38
    miques
    1.27
    アウト
    1.23
     hemma
    1.22
     Ganes
    1.20
    焢
    1.20
    珐
    1.19
     alltså
    1.19
    sigen
    1.14
    ポジション
    1.13
    Activations Density 0.002%

    No Known Activations