© 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. 34-GEMMASCOPE-RES-131K
    7. 83867
    Prev
    Next
    INDEX
    Explanations

    double-header, nightcap, in recent years, translocation

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

    The neuron strongly responds to numeric game or schedule details in sports write-ups—things like inning numbers, game one/two of a doubleheader, or other event timing and numbering phrases.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    DropDownList
    -0.81
     privileged
    -0.77
    giène
    -0.77
     consumables
    -0.75
    رب
    -0.75
     kelapa
    -0.74
    FormUrlEncoded
    -0.74
     represented
    -0.74
     medži
    -0.73
    LayoutStyle
    -0.71
    POSITIVE LOGITS
     double
    2.23
    double
    1.68
     Double
    1.60
     twin
    1.58
     doble
    1.55
     DOUBLE
    1.46
     DH
    1.36
    Double
    1.33
     двой
    1.28
    ダブル
    1.25
    Activations Density 0.019%

    No Known Activations