© 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. 8610
    Prev
    Next
    INDEX
    Explanations

    subproject definition

    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
    </u>
    -1.73
    Arcane
    -1.39
     tačiau
    -1.34
     gdyby
    -1.30
     todėl
    -1.26
     прине
    -1.24
    狍
    -1.24
    assem
    -1.24
     fotó
    -1.23
    }$.
    -1.23
    POSITIVE LOGITS
    價格
    1.60
    7
    1.52
    アレルギー
    1.48
    说是
    1.47
     intitulé
    1.45
    鲼
    1.44
     appelé
    1.42
     recomendada
    1.38
    5
    1.38
    well
    1.38
    Activations Density 0.022%

    No Known Activations