Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 15105
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Вели
    1.08
    лю
    0.99
    Лю
    0.95
    ани
    0.94
    MOVE
    0.94
    SCO
    0.93
    ๆ
    0.92
    หล
    0.91
    Сто
    0.90
     воору
    0.90
    POSITIVE LOGITS
     automaty
    1.31
     hata
    1.28
     livet
    1.24
     gleichzeitig
    1.19
     σαν
    1.18
     wahrscheinlich
    1.17
     öyle
    1.16
     sashimi
    1.15
     dems
    1.15
     lask
    1.15
    Activations Density 0.000%

    No Known Activations