© 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. 108463
    Prev
    Next
    INDEX
    Explanations

    . or following words

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

    This neuron detects numeric literals (numbers) 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
    värr
    -0.84
     тук
    -0.79
    的身影
    -0.77
     finely
    -0.77
    İş
    -0.75
    ungkin
    -0.75
    Liquid
    -0.75
    ⸼
    -0.75
    锂
    -0.75
     vời
    -0.74
    POSITIVE LOGITS
    sives
    0.77
     .............
    0.74
     .........
    0.74
    сколько
    0.73
    łow
    0.72
     --->
    0.72
    Spieler
    0.72
     st
    0.72
    ToMany
    0.71
    шо
    0.71
    Activations Density 0.000%

    No Known Activations