© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26039
    Prev
    Next
    INDEX
    Explanations

    Event Introduction Hosting

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

    The neuron primarily responds to numeric tokens (i.e. sequences of digits).

    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
     your
    -1.32
    様な
    -1.28
     our
    -1.25
     a
    -1.18
    ursos
    -1.15
     not
    -1.12
    為に
    -1.09
    際には
    -1.09
    づけ
    -1.07
    様に
    -0.98
    POSITIVE LOGITS
    がありますが
    1.59
    サーチ
    1.45
    Curios
    1.45
    についても
    1.36
    があります
    1.33
    Gön
    1.27
    があるので
    1.25
     заявил
    1.23
    但这
    1.22
    前は
    1.21
    Activations Density 0.003%

    No Known Activations