© 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. 11954
    Prev
    Next
    INDEX
    Explanations

    seismic activity

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

    The neuron strongly detects the string “seismic” (in any casing or split across subword tokens) in the 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_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
    tenham
    -0.77
     מא
    -0.73
     Drew
    -0.73
     swing
    -0.73
    simplex
    -0.73
    etcode
    -0.71
    $*
    -0.70
    Switch
    -0.69
    ’
    -0.69
    initializeApp
    -0.68
    POSITIVE LOGITS
    diano
    0.69
     Bonita
    0.68
     qualification
    0.68
    カテゴリ
    0.68
    WEDNESDAY
    0.67
     Juarez
    0.66
     ikat
    0.65
    笑着
    0.65
    详细信息
    0.64
     Vener
    0.63
    Activations Density 0.055%

    No Known Activations