© 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. 8956
    Prev
    Next
    INDEX
    Explanations

    consult with a professional

    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
     etc
    1.41
    等の
    1.39
     উক্ত
    1.26
    にて
    1.19
     इत्यादि
    1.17
    しております
    1.16
     সকল
    1.16
    /
    1.14
    等を
    1.13
    であった
    1.13
    POSITIVE LOGITS
     billionaire
    2.31
    糟糕
    2.08
     booze
    2.05
     nonprofits
    1.97
     hipster
    1.95
     millennials
    1.95
     lackluster
    1.95
     Obamacare
    1.95
     nonprofit
    1.93
     Midwestern
    1.93
    Activations Density 0.172%

    No Known Activations