© 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. 34-GEMMASCOPE-RES-131K
    7. 84349
    Prev
    Next
    INDEX
    Explanations

    names with suffixes like Roux, -insky, -ano

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

    The neuron fires on numeric tokens—standalone digits or numbers (e.g. years, page counts, statistics).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     by
    -3.50
    by
    -1.50
     will
    -1.20
     توسط
    -1.18
     etc
    -1.18
     should
    -1.13
     either
    -1.13
    <eos>
    -1.11
     must
    -1.09
    ById
    -1.08
    POSITIVE LOGITS
     reprinted
    1.18
     farba
    1.13
     Contributing
    1.13
     zdroj
    1.12
     rése
    1.08
     trám
    1.08
     exklu
    1.08
     publié
    1.07
     dévelo
    1.07
     maquilla
    1.06
    Activations Density 0.106%

    No Known Activations