© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 29
    Prev
    Next
    INDEX
    Explanations

    That's valid

    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_17_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
     South
    1.16
    美國
    1.16
     southeastern
    1.15
     Southeastern
    1.14
    美国
    1.12
     California
    1.11
     Australia
    1.11
    南
    1.09
     International
    1.09
     Amerika
    1.07
    POSITIVE LOGITS
     semblance
    0.78
     exacte
    0.73
     ticking
    0.72
    simple
    0.72
     darn
    0.71
     figuring
    0.71
     повин
    0.70
     يلا
    0.68
    potential
    0.68
     stuff
    0.68
    Activations Density 0.921%

    No Known Activations