© 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. 54324
    Prev
    Next
    INDEX
    Explanations

    integrated circuits

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

    The neuron activates on numeric tokens—particularly measurement values, model numbers, voltages, currents, or other technical quantities.

    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
    CommandType
    -0.86
    政府
    -0.85
    ੧
    -0.83
    +");
    -0.83
    ISTOL
    -0.81
    GCD
    -0.79
     géographie
    -0.77
    зани
    -0.77
     дороги
    -0.76
     UTF
    -0.76
    POSITIVE LOGITS
     labeled
    0.93
     silks
    0.89
     IC
    0.84
     located
    0.84
     显
    0.81
     U
    0.80
     Q
    0.80
    従業
    0.79
    labeled
    0.75
     labelled
    0.74
    Activations Density 0.033%

    No Known Activations