© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103576
    Prev
    Next
    INDEX
    Explanations

    legal citations and identifiers

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

    The main thing this neuron does is detect numeric tokens—especially multi‐digit numbers such as years, version numbers, document references, and other numeric identifiers.

    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
    ław
    -0.85
     Taylor
    -0.82
    lau
    -0.81
    Taylor
    -0.75
    local
    -0.73
    laf
    -0.73
    ea
    -0.73
    ueras
    -0.72
     labor
    -0.71
    figsize
    -0.69
    POSITIVE LOGITS
     Tulane
    0.82
     ameste
    0.72
    kệ
    0.71
    閻
    0.68
     Entwurf
    0.68
    ală
    0.67
    INTS
    0.67
     PPM
    0.66
    Frente
    0.66
    Waff
    0.66
    Activations Density 0.051%

    No Known Activations