© 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. 34057
    Prev
    Next
    INDEX
    Explanations

    scores and counts

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

    The neuron selectively activates on numerical tokens—scores, dates, statistics, and other numeric figures in sports‐report style 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
    ,
    -1.31
     [
    -1.16
    !
    -1.14
     لأنه
    -1.09
     by
    -1.08
     when
    -1.06
    Many
    -1.05
    ねぎ
    -1.04
     many
    -1.03
     or
    -1.02
    POSITIVE LOGITS
     pleaf
    1.33
    XCTAssertEqual
    1.28
    terrasse
    1.18
     JOSEPH
    1.14
    -};
    1.13
     يكن
    1.13
    archiwizowane
    1.12
     familien
    1.10
    =?";
    1.09
     eenig
    1.09
    Activations Density 0.036%

    No Known Activations