© 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. 14606
    Prev
    Next
    INDEX
    Explanations

    more than a movie

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

    The main thing this neuron does is detect numeric tokens or numerical expressions (e.g. integers and decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     السياس
    -1.38
    怀里
    -1.25
    colección
    -1.24
     operar
    -1.23
    すすめ
    -1.20
    Discography
    -1.16
     nutrition
    -1.12
     reservado
    -1.11
    aggregation
    -1.11
     lengu
    -1.10
    POSITIVE LOGITS
     někter
    1.30
     IMPRO
    1.28
    логии
    1.26
     overall
    1.25
    全体的に
    1.23
    quilo
    1.21
     hauptsächlich
    1.20
    overall
    1.19
     względem
    1.19
     بیشتر
    1.18
    Activations Density 0.035%

    No Known Activations