© 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. 87065
    Prev
    Next
    INDEX
    Explanations

    numeric string operations

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

    The neuron fires strongly on numeric elements—digits, numeric literals, and arithmetic‐ or number‐related tokens.

    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
    вної
    -0.76
    äre
    -0.73
     miles
    -0.71
    hörer
    -0.70
    removeAttr
    -0.70
    konferenz
    -0.69
     논
    -0.68
     hearing
    -0.68
     เค
    -0.67
    ladas
    -0.67
    POSITIVE LOGITS
     strconv
    1.80
     Integer
    1.80
    strconv
    1.73
    itoa
    1.70
    Integer
    1.42
     integer
    1.34
    NSNumber
    1.21
    整数
    1.09
     Convert
    1.09
     ito
    1.06
    Activations Density 0.017%

    No Known Activations