© 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. 10-GEMMASCOPE-RES-131K
    7. 119017
    Prev
    Next
    INDEX
    Explanations

    academic tasks

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

    The neuron detects numeric tokens (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
    ’
    -1.47
     the
    -1.36
     through
    -1.36
     various
    -1.33
    がありますが
    -1.28
     ofertas
    -1.27
     types
    -1.25
    ptid
    -1.16
    她在
    -1.16
     actions
    -1.16
    POSITIVE LOGITS
     czerwca
    1.62
     апреля
    1.34
    eseen
    1.33
     сентября
    1.32
     июня
    1.31
    asjon
    1.30
     tejidos
    1.30
     съдържа
    1.29
    Resizable
    1.28
     Setiap
    1.28
    Activations Density 0.026%

    No Known Activations