© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 606
    Prev
    Next
    INDEX
    Explanations

    months and dates

    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
     we
    -1.60
    odori
    -1.37
     emlé
    -1.34
     déclare
    -1.34
    itando
    -1.30
     custos
    -1.30
    再一次
    -1.30
     autorisation
    -1.30
     inova
    -1.29
    市内
    -1.28
    POSITIVE LOGITS
     that
    2.23
     and
    1.80
     or
    1.54
     bluz
    1.41
     dekol
    1.38
     both
    1.32
     tunik
    1.30
    </em>
    1.28
     each
    1.27
     which
    1.26
    Activations Density 0.078%

    No Known Activations