© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43658
    Prev
    Next
    INDEX
    Explanations

    SQL query

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

    The neuron fires on numeric expressions (tokens representing numbers and their immediate context).

    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
     такую
    -1.45
     with
    -1.45
     also
    -1.40
    We
    -1.34
    ant
    -1.32
    ()",
    -1.28
     of
    -1.28
    ينا
    -1.27
     about
    -1.27
     miliardi
    -1.24
    POSITIVE LOGITS
     acoged
    1.39
     风景
    1.32
     развитии
    1.31
     режиме
    1.27
     könnt
    1.27
     encontrarás
    1.27
     diseñar
    1.27
     estudia
    1.26
    ᗪ
    1.23
    背影
    1.22
    Activations Density 0.046%

    No Known Activations