© 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. 57475
    Prev
    Next
    INDEX
    Explanations

    subject to license

    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
     and
    -2.11
    他们
    -1.34
     &
    -1.31
     וש
    -1.31
    <0xEA>
    -1.31
    {~
    -1.28
    酝
    -1.25
    และ
    -1.16
     gastronomía
    -1.16
    conde
    -1.14
    POSITIVE LOGITS
     have
    1.48
     huden
    1.38
     needed
    1.34
     Commencez
    1.28
     doesn
    1.28
     Dernière
    1.26
     chiara
    1.26
    </em>
    1.23
     egentlig
    1.22
     enemmän
    1.21
    Activations Density 0.188%

    No Known Activations