© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79011
    Prev
    Next
    INDEX
    Explanations

    zero or digits

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

    The neuron responds to numeric tokens—especially multi‐digit numbers and codes.

    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
     association
    -0.76
    pahan
    -0.73
    fifty
    -0.73
     Drž
    -0.73
    hundreds
    -0.72
    ÈS
    -0.71
    diman
    -0.71
     twenties
    -0.71
     Emergence
    -0.71
     terce
    -0.70
    POSITIVE LOGITS
     zero
    1.91
    ０
    1.80
     cero
    1.44
    Zero
    1.34
     Zero
    1.30
     ۰
    1.30
    0
    1.24
     ZERO
    1.19
    zero
    1.16
     zéro
    1.02
    Activations Density 0.170%

    No Known Activations