© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130415
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric literals (including integers and decimals) in the document.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    type `token`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     chcą
    -1.04
     unaweza
    -0.98
     utaf
    -0.86
     μή
    -0.86
     hivyo
    -0.85
     maisha
    -0.85
     subsequently
    -0.84
     does
    -0.84
    let
    -0.83
     consequently
    -0.83
    POSITIVE LOGITS
    Ouverture
    1.05
     melang
    1.01
     oeil
    1.00
    Meld
    0.98
    羸
    0.96
    
    0.96
     œil
    0.95
     actrice
    0.95
     cebo
    0.95
     Britannica
    0.93
    Activations Density 0.001%

    No Known Activations