© 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. 10-GEMMASCOPE-RES-131K
    7. 75665
    Prev
    Next
    INDEX
    Explanations

    section or SEC

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

    This neuron consistently activates on numeric tokens—especially decimal numbers—used in section headings, version identifiers, dates, and similar structural metadata.

    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
    <
    -2.38
     now
    -2.02
    .’
    -2.02
        
    -1.92
     to
    -1.89
     was
    -1.84
    ’.
    -1.83
     you
    -1.79
    _
    -1.77
    begin
    -1.73
    POSITIVE LOGITS
    寕
    2.41
    selbe
    2.17
    擽
    2.16
     harten
    2.03
    ྜ
    2.02
     gömlek
    1.99
    桖
    1.98
     hırka
    1.98
    蹀
    1.91
    錞
    1.91
    Activations Density 0.000%

    No Known Activations