© 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. 22-GEMMASCOPE-RES-131K
    7. 98543
    Prev
    Next
    INDEX
    Explanations

    function, sql, code, list

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

    The neuron primarily fires on numeric literals and digit sequences (numbers) 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_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
    ;
    -1.58
     Uniwers
    -1.53
    -
    -1.44
     œufs
    -1.41
     to
    -1.38
     from
    -1.31
    média
    -1.30
     Projektu
    -1.29
    先は
    -1.28
    趼
    -1.28
    POSITIVE LOGITS
    D
    1.57
    n
    1.52
     magnificent
    1.45
    B
    1.41
    T
    1.38
    G
    1.38
    N
    1.35
    J
    1.35
    a
    1.34
    I
    1.34
    Activations Density 0.039%

    No Known Activations