© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 38002
    Prev
    Next
    INDEX
    Explanations

    date: or callback(

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

    The neuron fires on document metadata fields, section headings, and other label‐style tokens (e.g. “date,” “Decision,” “Judgment,” “Decided,” version or heading markers).

    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
     közül
    -0.75
    Artifact
    -0.68
    ActionEvent
    -0.66
     Aussicht
    -0.65
    стюм
    -0.65
     Symp
    -0.63
    ワン
    -0.63
    賊
    -0.63
    ソング
    -0.62
     Vorm
    -0.62
    POSITIVE LOGITS
     McMahon
    0.73
     viejo
    0.70
     枝
    0.67
    yczne
    0.67
     mensen
    0.66
     histórico
    0.66
     Sabrina
    0.65
    iesta
    0.65
    askan
    0.64
     Tind
    0.64
    Activations Density 0.086%

    No Known Activations