© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129952
    Prev
    Next
    INDEX
    Explanations

    names ending in 's' followed by institutions

    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
    ギュア
    -2.20
    そういえば
    -2.17
    鉏
    -2.14
    Its
    -2.13
    鬭
    -2.00
    ⩩
    -1.97
     verlie
    -1.95
    やろ
    -1.95
    Their
    -1.94
     rembour
    -1.93
    POSITIVE LOGITS
     were
    2.27
    出了一
    2.11
     I
    2.02
    遏
    2.02
     extravagant
    1.91
     of
    1.91
    国防
    1.91
     '
    1.90
     fateful
    1.86
     s
    1.85
    Activations Density 0.007%

    No Known Activations