© 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. 10-GEMMASCOPE-RES-131K
    7. 100857
    Prev
    Next
    INDEX
    Explanations

    names, roles, or places

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

    The neuron activates on numeric tokens (e.g. years, ages, and other digit-based values) 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
    ;
    -1.12
    tą
    -1.06
     utilisé
    -1.06
    ać
    -1.06
     operation
    -1.04
     širo
    -1.04
    pring
    -1.03
     website
    -1.02
     today
    -1.02
    ouille
    -1.02
    POSITIVE LOGITS
    PROTOBUF
    1.27
     после
    1.17
    ятся
    1.09
     क्यों
    1.09
     despite
    1.07
     mendatang
    1.06
     árbitro
    1.06
    Despite
    1.06
     cucchiai
    1.05
     Hvor
    1.02
    Activations Density 0.246%

    No Known Activations