© 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. 7-GEMMASCOPE-2-RES-16K
    7. 129
    Prev
    Next
    INDEX
    Explanations

    concepts and consequences

    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_7_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
     ブリヂストン
    1.86
    )|$(
    1.83
     สืบค้นเมื่อ
    1.80
     オール
    1.75
     ਹਨ
    1.74
    ллер
    1.72
     Bóng
    1.72
     높아
    1.72
    놁
    1.69
     苏
    1.69
    POSITIVE LOGITS
    ier
    1.65
    spend
    1.47
    myst
    1.45
    ic
    1.45
    შ
    1.38
    সভার
    1.37
    saver
    1.36
    bump
    1.36
    son
    1.33
    prett
    1.33
    Activations Density 8.200%

    No Known Activations