© 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. 73629
    Prev
    Next
    INDEX
    Explanations

    double directing ignoring

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

    This neuron responds to high-level structural or title elements in the text—section headings, metadata markers, or document titles.

    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
     எ
    -0.78
    恙
    -0.75
     Localization
    -0.73
    อ้าง
    -0.71
     derives
    -0.71
    رسال
    -0.69
    erobic
    -0.69
     amber
    -0.69
    DateTimeFormat
    -0.69
     Ско
    -0.68
    POSITIVE LOGITS
    ViewSet
    0.79
     OpenAPI
    0.79
    ZA
    0.78
    ilever
    0.77
     Fresh
    0.77
    ステム
    0.76
    ENCES
    0.76
    llen
    0.76
    skiej
    0.75
     slap
    0.75
    Activations Density 0.004%

    No Known Activations