© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 36631
    Prev
    Next
    INDEX
    Explanations

    document section headers

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

    The neuron activates on numeric tokens or numerical expressions (e.g. numbers, percentages, years).

    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
    ditionally
    -1.33
     Bárbara
    -1.27
    Germany
    -1.26
    demás
    -1.19
    Especificações
    -1.15
     Óscar
    -1.13
    Согласно
    -1.13
     войск
    -1.13
     penghar
    -1.13
     artikkelen
    -1.13
    POSITIVE LOGITS
     why
    1.63
     our
    1.23
     executar
    1.19
     what
    1.16
     diversos
    1.15
     Doesn
    1.13
     mostrando
    1.11
     ativar
    1.11
     представлены
    1.11
     praticamente
    1.10
    Activations Density 0.003%

    No Known Activations