© 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. 118920
    Prev
    Next
    INDEX
    Explanations

    The Times newspaper

    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
    愎
    -2.88
    ,”
    -2.80
     verbessert
    -2.73
    蟜
    -2.69
    を購入
    -2.63
    を見つけ
    -2.53
    也算是
    -2.52
    tedì
    -2.52
    也算
    -2.52
    あんまり
    -2.39
    POSITIVE LOGITS
    it
    2.95
    ar
    2.94
    il
    2.39
    ling
    2.38
    2.30
    le
    2.27
    io
    2.22
    ids
    2.22
    ma
    2.19
    man
    2.19
    Activations Density 0.005%

    No Known Activations