© 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. 10-GEMMASCOPE-RES-131K
    4. 41306
    Prev
    Next
    INDEX
    Explanations

    sought after

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

    The neuron selectively activates on the past‐tense form of “seek,” i.e. the word “sought.”

    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
    鬭
    -3.31
    鱚
    -3.20
    蕯
    -2.97
     ujar
    -2.89
     cuci
    -2.75
    Wady
    -2.70
    ⃙
    -2.66
    archiwizowane
    -2.59
    羕
    -2.53
     handlar
    -2.44
    POSITIVE LOGITS
    ↵↵
    3.84
    '
    2.84
    "
    2.61
    HomeAsUpEnabled
    2.55
    <i>
    2.50
    ный
    2.41
     is
    2.36
    ༀ
    2.33
    ные
    2.33
    痔
    2.31
    Activations Density 0.002%

    No Known Activations