© 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. 1014
    Prev
    Next
    INDEX
    Explanations

    clear cache or if condition

    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
    Otros
    1.17
    ín
    1.16
    ülő
    1.16
    मति
    1.14
    ő
    1.14
    első
    1.14
    untuk
    1.13
    вЂ
    1.13
    rograman
    1.13
    Lib
    1.12
    POSITIVE LOGITS
     没有
    1.18
     由于
    1.15
     目前
    1.15
     tension
    1.11
     做
    1.09
     render
    1.09
     按
    1.08
     assess
    1.07
     test
    1.06
     除了
    1.06
    Activations Density 0.002%

    No Known Activations