© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130003
    Prev
    Next
    INDEX
    Explanations

    quality control and acceptable limits

    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
    拍了拍
    -1.37
     afront
    -1.26
     déplacer
    -1.23
     propiedades
    -1.16
    inders
    -1.13
     informes
    -1.11
    のほうが
    -1.11
    EDES
    -1.10
     prawdzi
    -1.10
     apporter
    -1.10
    POSITIVE LOGITS
     when
    1.35
     before
    1.30
     as
    1.20
    ̍
    1.10
    </td>
    1.10
    ódromo
    1.09
     during
    1.09
    plyr
    1.09
    itées
    1.09
    ultimo
    1.07
    Activations Density 0.073%

    No Known Activations