© 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. 13-GEMMASCOPE-2-RES-16K
    7. 850
    Prev
    Next
    INDEX
    Explanations

    filled with or covered by

    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
    பொ
    1.15
    对应的
    1.12
    ٹ
    1.12
    가의
    1.10
     തുടർ
    1.09
    ကို
    1.09
    ड़
    1.09
    柣
    1.09
    ის
    1.08
     richiesta
    1.05
    POSITIVE LOGITS
    by
    1.40
     by
    1.38
    bym
    1.30
    ness
    1.14
    ly
    1.09
     By
    1.06
    da
    1.03
     oleh
    1.00
    ependent
    1.00
    By
    0.97
    Activations Density 0.937%

    No Known Activations