© 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. 13567
    Prev
    Next
    INDEX
    Explanations

    type or kind

    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
    GORITH
    -1.31
     conceptual
    -1.28
    </strong>
    -1.28
    ✆
    -1.23
     from
    -1.20
     moral
    -1.19
    金币
    -1.19
    𝗙
    -1.17
    那时
    -1.15
    躂
    -1.15
    POSITIVE LOGITS
     why
    1.62
     varför
    1.33
    tività
    1.31
     erfolgreiche
    1.30
    Activités
    1.27
     &
    1.27
     whether
    1.27
     cieka
    1.26
     spannende
    1.24
     diversos
    1.23
    Activations Density 0.071%

    No Known Activations