© 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. 45735
    Prev
    Next
    INDEX
    Explanations

    mean +/- SD

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

    This neuron specializes in detecting numeric values and quantitative measurements (e.g., numbers and statistics) in the text.

    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
     crouch
    -0.81
     crou
    -0.77
    tosí
    -0.77
     Deity
    -0.73
    琉璃
    -0.73
     Đình
    -0.72
     ($("#
    -0.72
    ussis
    -0.72
    uelta
    -0.71
    uspiel
    -0.70
    POSITIVE LOGITS
     standard
    4.59
     Standard
    3.98
    standard
    3.91
    Standard
    3.84
    标准
    3.77
     стандарт
    3.52
     Std
    3.33
    標準
    3.33
     std
    3.31
    Std
    3.31
    Activations Density 0.105%

    No Known Activations