© 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. 100176
    Prev
    Next
    INDEX
    Explanations

    closing punctuation and grouping symbols

    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
     sorella
    -1.30
    かなぁ
    -1.28
    Sejarah
    -1.26
     fiance
    -1.23
    〜。
    -1.22
     Those
    -1.21
    Those
    -1.18
    ujudkan
    -1.17
     там
    -1.13
     our
    -1.12
    POSITIVE LOGITS
    </strong>
    1.48
    骉
    1.41
    críbete
    1.34
    ();)
    1.30
    )
    1.30
    te
    1.27
    pheric
    1.27
     either
    1.25
    entered
    1.25
    me
    1.22
    Activations Density 0.127%

    No Known Activations