© 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. 85454
    Prev
    Next
    INDEX
    Explanations

    AJumSHOWTrumpFordBackWhenRonOneOvernight

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

    This neuron highlights standalone numerical values (both integers and decimals) 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
     ‘
    -2.20
    S
    -2.09
    e
    -2.06
    er
    -2.03
    ….
    -1.95
    M
    -1.90
    E
    -1.90
    C
    -1.89
     “
    -1.88
    G
    -1.83
    POSITIVE LOGITS
    adakan
    1.80
    Etimo
    1.77
    doppel
    1.71
    indahan
    1.70
     Wartawan
    1.66
     sentarse
    1.65
    ği
    1.65
     فنا
    1.63
    dengar
    1.63
    értel
    1.61
    Activations Density 0.019%

    No Known Activations