© 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. 277
    Prev
    Next
    INDEX
    Explanations

    is essential, is based, is able

    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
    benzoyl
    0.47
     Mere
    0.44
     Big
    0.44
     Beware
    0.44
    rune
    0.43
    huri
    0.43
    蒡
    0.42
    지
    0.42
     sleepless
    0.42
     nasty
    0.42
    POSITIVE LOGITS
    对应的
    0.62
     }^{*}
    0.56
    对应
    0.53
    tidak
    0.52
    ্রয়
    0.50
    NotExist
    0.50
     }^{-
    0.50
    ället
    0.48
    lerinde
    0.48
    ném
    0.48
    Activations Density 1.315%

    No Known Activations