© 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. 84503
    Prev
    Next
    INDEX
    Explanations

    comma followed by other punctuation

    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
     it
    -2.14
     our
    -1.73
     \
    -1.59
    肫
    -1.48
     umożli
    -1.45
    谖
    -1.45
    expiresIn
    -1.37
     odpowied
    -1.35
    鐒
    -1.35
     люб
    -1.34
    POSITIVE LOGITS
     "
    1.81
    </sup>
    1.52
    這
    1.47
    この
    1.39
     что
    1.30
    这
    1.30
    ový
    1.29
     dát
    1.28
    (?)
    1.27
     rather
    1.26
    Activations Density 0.008%

    No Known Activations