© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1273
    Prev
    Next
    INDEX
    Explanations

    formal document headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     absolutely
    1.41
     because
    1.28
     we
    1.22
     sedan
    1.21
     не
    1.21
     brutal
    1.18
     a
    1.17
     doesn
    1.16
     it
    1.16
     cowboy
    1.16
    POSITIVE LOGITS
    Beschreibung
    1.29
    関連項目
    1.23
    攷
    1.21
    description
    1.19
     Beschreibung
    1.18
    備考
    1.13
    Descrição
    1.12
    방법
    1.12
    Acknowledgements
    1.11
    Daten
    1.09
    Activations Density 0.062%

    No Known Activations