© 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. 129896
    Prev
    Next
    INDEX
    Explanations

    journal citations and references

    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
    ــ
    -1.32
     ـ
    -1.32
     Tatsache
    -1.28
    dekor
    -1.28
     travaillé
    -1.22
    就是
    -1.21
     décidé
    -1.21
     sicheren
    -1.20
    所有
    -1.19
    了
    -1.19
    POSITIVE LOGITS
     by
    1.76
     even
    1.48
     have
    1.43
     on
    1.30
     for
    1.29
     had
    1.28
     so
    1.25
     Presidente
    1.20
     with
    1.20
     that
    1.19
    Activations Density 0.072%

    No Known Activations