© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100003
    Prev
    Next
    INDEX
    Explanations

    universities and institutional addresses

    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
    ’
    -3.13
    ні
    -2.98
    }
    -2.88
    は
    -2.61
    ……」
    -2.61
     \_
    -2.50
     (;;)
    -2.48
    та
    -2.45
    It
    -2.34
    ,"
    -2.33
    POSITIVE LOGITS
    蚡
    2.84
    臯
    2.64
    毉
    2.55
     estadía
    2.45
    鳧
    2.45
    鱚
    2.41
    螣
    2.39
     fenó
    2.38
    ዣ
    2.38
    𐀀
    2.31
    Activations Density 0.008%

    No Known Activations