© 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. 19068
    Prev
    Next
    INDEX
    Explanations

    game, prediction, language, code

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

    The neuron fires on numeric tokens—i.e. literal numbers (and number‐heavy tokens like CSS numeric values, scale factors, coordinates, durations, etc.).

    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
    ֵּ
    -1.77
    ִּ
    -1.77
    ַּ
    -1.70
    ֶּ
    -1.69
    ּוֹ
    -1.64
     problems
    -1.53
     it
    -1.52
    ִּי
    -1.43
     чемпи
    -1.42
     adjusted
    -1.37
    POSITIVE LOGITS
    <b>
    1.52
     dziś
    1.52
     pegatinas
    1.52
     continuación
    1.51
     dzisiaj
    1.50
     wciąż
    1.48
     sugerencias
    1.47
    ׇ
    1.47
     regulación
    1.44
    节奏
    1.42
    Activations Density 0.004%

    No Known Activations