© 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. 22-GEMMASCOPE-RES-131K
    7. 38708
    Prev
    Next
    INDEX
    Explanations

    struct definitions

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

    The neuron fires on numeric literals 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
     uzyskać
    -1.36
    稔
    -1.30
     indicate
    -1.26
    پاسخ
    -1.25
    崛
    -1.25
     znaleźć
    -1.23
    見えます
    -1.23
     På
    -1.23
     would
    -1.20
     That
    -1.19
    POSITIVE LOGITS
    *
    1.38
     évidemment
    1.34
     cuantos
    1.28
     quels
    1.25
     ZIM
    1.22
     BRAD
    1.20
     malheureusement
    1.20
    .
    1.20
    (
    1.19
    &
    1.18
    Activations Density 0.005%

    No Known Activations