© 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. 10-GEMMASCOPE-RES-131K
    7. 59173
    Prev
    Next
    INDEX
    Explanations

    effort and attempt

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

    The neuron activates on numeric tokens—both integers and decimals—wherever numbers (e.g., scores, counts, or measurements) appear 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_10/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
     vérification
    -1.71
    鱚
    -1.70
    tocks
    -1.65
    起来了
    -1.64
    
    -1.59
     détermination
    -1.55
    atação
    -1.53
    能让
    -1.53
     vendeur
    -1.51
     siena
    -1.51
    POSITIVE LOGITS
     but
    1.65
    abatic
    1.57
    8
    1.45
    [
    1.41
    家伙
    1.41
     out
    1.39
    ان
    1.36
    ,.
    1.36
    ,...
    1.36
    an
    1.35
    Activations Density 0.022%

    No Known Activations