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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 111107
    Prev
    Next
    INDEX
    Explanations

    code and testing structures

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

    The neuron activates on numeric literals (sequences of digits) 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
     餅
    -0.95
    êcher
    -0.94
    Cechy
    -0.85
    ⇐
    -0.85
     grossesse
    -0.84
     XXIII
    -0.84
    readonly
    -0.82
    っしゃ
    -0.81
    tovní
    -0.81
    なのかな
    -0.81
    POSITIVE LOGITS
     if
    0.97
     when
    0.95
    に
    0.88
    などを
    0.83
     mentioned
    0.83
    if
    0.81
     geno
    0.79
     accurately
    0.78
     اضافه
    0.77
    侘
    0.77
    Activations Density 0.004%

    No Known Activations