© 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-65K
    7. 634
    Prev
    Next
    INDEX
    Explanations

    game, points, slots, or book

    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_65k_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
    戟
    1.46
    движи
    1.45
    н
    1.29
    т
    1.28
     echoes
    1.26
    シ
    1.24
    П
    1.22
     presented
    1.22
     блока
    1.20
     touches
    1.19
    POSITIVE LOGITS
    kal
    1.54
     diesen
    1.53
    inor
    1.53
     wirklich
    1.52
     yıll
    1.49
     Jahrze
    1.49
     उचल
    1.46
    menin
    1.45
     Wochen
    1.44
    ഋ
    1.43
    Activations Density 0.000%

    No Known Activations