© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32461
    Prev
    Next
    INDEX
    Explanations

    loop iteration variable

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

    The neuron is primarily detecting numeric tokens (integer literals) 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
     something
    -0.86
     someone
    -0.83
     January
    -0.81
    cartera
    -0.78
     нещо
    -0.78
    点点头
    -0.77
     anfangs
    -0.77
     ml
    -0.77
    wasm
    -0.76
     ONE
    -0.75
    POSITIVE LOGITS
    elten
    0.94
    꽃
    0.92
    bagai
    0.87
    slot
    0.82
    öffnung
    0.82
     reactors
    0.82
     finner
    0.81
    Преимущества
    0.81
    ミナル
    0.79
    🧭
    0.79
    Activations Density 0.005%

    No Known Activations