© 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. 90911
    Prev
    Next
    INDEX
    Explanations

    Kane, Caine, Cain, pane, cane

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

    The neuron activates on multi‐digit numeric tokens (e.g. years, counts, 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
     глав
    -0.78
    fD
    -0.70
    Welp
    -0.69
     تل
    -0.69
     UMA
    -0.69
     extreme
    -0.68
    rm
    -0.68
     quil
    -0.67
    lado
    -0.66
    properties
    -0.66
    POSITIVE LOGITS
    Sugar
    0.84
    ഉ
    0.82
     cukru
    0.80
     toad
    0.79
    magine
    0.79
     sugar
    0.78
     Manajemen
    0.77
     PLACE
    0.76
     selalu
    0.75
    varo
    0.75
    Activations Density 0.019%

    No Known Activations