© 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. 124096
    Prev
    Next
    INDEX
    Explanations

    design and designers

    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
     permitió
    -1.32
     you
    -1.31
     istimewa
    -1.30
    Various
    -1.30
    </h2>
    -1.28
     your
    -1.25
    Using
    -1.20
    𝟐
    -1.16
     there
    -1.16
    奩
    -1.16
    POSITIVE LOGITS
    </u>
    1.41
    \}$
    1.33
     भी
    1.25
    Taurus
    1.24
    Carex
    1.23
    inafter
    1.21
    ніципа
    1.21
    斡
    1.20
    Voucher
    1.19
    циям
    1.19
    Activations Density 0.034%

    No Known Activations