© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 104712
    Prev
    Next
    INDEX
    Explanations

    sports times and scores

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

    The neuron fires on numeric tokens—especially measurements and statistical values (e.g., times, distances, scores).

    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
    Item
    -1.23
    >−</
    -1.16
     your
    -1.09
    Option
    -1.09
    Activity
    -1.08
    ('-'
    -1.07
     volont
    -1.05
    ongono
    -1.02
     sandalias
    -1.02
    дки
    -1.02
    POSITIVE LOGITS
    توضیحات
    1.33
     späteren
    1.17
     konusunda
    1.17
    paymentMethod
    1.14
     очень
    1.14
    TRIBUN
    1.13
     desconoc
    1.12
    معرفی
    1.11
    Komentar
    1.10
    messageId
    1.09
    Activations Density 0.004%

    No Known Activations