© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6867
    Prev
    Next
    INDEX
    Explanations

    sequentially processing text, lists, or sequences

    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
     hangar
    1.19
     Bomber
    1.13
     हमला
    1.13
     memorial
    1.12
     adicionar
    1.10
     acrescent
    1.10
    葬
    1.10
     landfill
    1.08
     bombers
    1.08
     hen
    1.07
    POSITIVE LOGITS
     gripped
    1.03
    湍
    1.00
     smoothly
    1.00
    oucí
    1.00
    匙
    0.98
     عج
    0.97
     ناول
    0.97
     терпе
    0.96
    Slow
    0.96
     Slow
    0.94
    Activations Density 0.237%

    No Known Activations