© 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. 40054
    Prev
    Next
    INDEX
    Explanations

    function calls and keywords

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

    The neuron fires on numeric literals (integer constants) in code.

    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
    maske
    -1.12
    vidades
    -1.11
     vorige
    -1.08
     zaman
    -1.07
    digkeit
    -1.04
    荭
    -1.04
     комбини
    -1.02
     Эти
    -1.01
     melk
    -1.00
    Эти
    -0.99
    POSITIVE LOGITS
     (
    1.29
     Popis
    1.24
     by
    1.19
     felé
    1.16
     budete
    1.16
     in
    1.14
     group
    1.13
     how
    1.10
     so
    1.07
     that
    1.05
    Activations Density 0.011%

    No Known Activations