© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78966
    Prev
    Next
    INDEX
    Explanations

    code structure and rules

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

    The neuron flags chunks of text or code that enumerate or discuss lint‐rule configurations (e.g. ESLint/TSLint rules sections).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     loyal
    -0.70
    切った
    -0.69
     shock
    -0.68
    gpu
    -0.67
     lowercase
    -0.66
     leek
    -0.66
     monog
    -0.66
     Fores
    -0.66
     люблю
    -0.66
     orphans
    -0.66
    POSITIVE LOGITS
     parser
    0.88
     парка
    0.85
    parser
    0.85
     konfigura
    0.85
    ucs
    0.81
    Ժ
    0.79
    COUVER
    0.79
     mistura
    0.77
     ему
    0.76
    TokenNameRPAREN
    0.75
    Activations Density 0.034%

    No Known Activations