© 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. 31857
    Prev
    Next
    INDEX
    Explanations

    minimum and maximum values

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

    The neuron specializes in spotting numeric tokens—especially multi‐digit numbers denoting years, measurements, counts, or other quantitative values.

    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
    enough
    -0.83
    llbracket
    -0.75
     Enough
    -0.75
     Saty
    -0.75
     requête
    -0.72
    vince
    -0.72
     Basket
    -0.71
    jsdelivr
    -0.71
     meilleure
    -0.71
    WORTH
    -0.71
    POSITIVE LOGITS
     minimum
    1.93
     a
    1.59
     минимум
    1.41
     mínimo
    1.18
     maximum
    1.18
     мини
    1.15
    minimum
    1.14
     міні
    1.07
     макси
    0.99
    MINIMUM
    0.95
    Activations Density 0.030%

    No Known Activations