© 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. 30920
    Prev
    Next
    INDEX
    Explanations

    programming code and queries

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

    This neuron detects the presence of C-style for-loop headers (the “for (int i …)” syntax) in code.

    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
     polig
    -0.77
    getIn
    -0.75
    ثي
    -0.74
    IGO
    -0.74
    !»
    -0.74
    leted
    -0.73
    onika
    -0.73
    ₃
    -0.72
    ос
    -0.72
     posture
    -0.72
    POSITIVE LOGITS
    RequestHandler
    0.86
    Fernseh
    0.84
    opes
    0.77
     Traducción
    0.77
     televisions
    0.75
     consoles
    0.75
     Edelman
    0.74
    ppure
    0.73
     bulletin
    0.73
     NTS
    0.72
    Activations Density 0.000%

    No Known Activations