© 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. 69494
    Prev
    Next
    INDEX
    Explanations

    throwback, throwaway, throwaway, Vodafone, Michael Curtis

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    <bos>
    -2.06
    俺は
    -2.03
    从未
    -1.93
    记住
    -1.90
    持續
    -1.89
    廝
    -1.88
    紓
    -1.88
    尋找
    -1.88
    裡的
    -1.86
    蛻
    -1.83
    POSITIVE LOGITS
    Ⴀ
    2.42
    ”、“
    2.17
    ”（
    2.13
    亊
    2.08
    ”？
    2.00
    谞
    2.00
    狁
    1.98
    的一
    1.92
    可不是
    1.90
    месте
    1.89
    Activations Density 0.001%

    No Known Activations