© 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. 20827
    Prev
    Next
    INDEX
    Explanations

    problem is that i don't know how

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

    The neuron specializes in spotting numeric literals (especially decimal or floating‐point numbers), with its activation roughly matching the number’s value.

    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
     in
    -2.38
     with
    -2.19
     of
    -2.03
     however
    -1.84
    in
    -1.76
     кстати
    -1.58
     also
    -1.55
     especially
    -1.55
     although
    -1.54
    It
    -1.52
    POSITIVE LOGITS
     sois
    1.78
     ſta
    1.62
     visites
    1.60
    noted
    1.57
     président
    1.57
    actéristi
    1.54
     formes
    1.53
    ܊
    1.52
    ⟞
    1.52
    ⎔
    1.51
    Activations Density 0.136%

    No Known Activations