© 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. 8553
    Prev
    Next
    INDEX
    Explanations

    signing method none

    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
     quoque
    -1.30
     some
    -1.29
    </tfoot>
    -1.26
    中略
    -1.24
    惱
    -1.23
     appareil
    -1.18
     cantora
    -1.18
    恼
    -1.16
     Mawr
    -1.16
     vín
    -1.15
    POSITIVE LOGITS
     then
    1.63
     it
    1.62
     &
    1.44
    selbe
    1.35
    </h6>
    1.32
     /
    1.30
    ễm
    1.30
     yPos
    1.27
    bertura
    1.27
    ệng
    1.25
    Activations Density 0.061%

    No Known Activations