© 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. 70403
    Prev
    Next
    INDEX
    Explanations

    new material types and applications

    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
     cappuccio
    -1.52
     Ähnliche
    -1.41
    鲼
    -1.34
    거나
    -1.32
     Daß
    -1.31
    um
    -1.30
     or
    -1.29
     wystarczy
    -1.29
     reeling
    -1.27
    톱
    -1.27
    POSITIVE LOGITS
     africains
    1.41
    </strong>
    1.30
     Châte
    1.23
     violon
    1.22
    THEN
    1.20
    鲠
    1.17
    tischen
    1.16
    Seeds
    1.14
     perú
    1.13
    ним
    1.13
    Activations Density 0.171%

    No Known Activations