© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11267
    Prev
    Next
    INDEX
    Explanations

    crossword clues and door questions

    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_7_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
    د
    1.77
    в
    1.63
    ب
    1.45
    OutOf
    1.43
    с
    1.42
     مق
    1.40
    狽
    1.40
    ा
    1.38
    ictal
    1.37
    かけて
    1.34
    POSITIVE LOGITS
     πρώ
    1.54
     preparación
    1.49
     remodeled
    1.48
     preparazione
    1.45
     Fernandes
    1.44
     Flemish
    1.42
     produzione
    1.39
    ீ
    1.38
     latter
    1.38
     préparation
    1.38
    Activations Density 0.003%

    No Known Activations