Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 88
    Prev
    Next
    INDEX
    Explanations

    solutions and advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_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
    ig
    0.66
    .
    0.57
    x
    0.57
    anter
    0.56
    et
    0.55
    ac
    0.54
    er
    0.53
     Sprinkle
    0.53
     refere
    0.52
    as
    0.52
    POSITIVE LOGITS
    Giá
    0.59
    україн
    0.59
     여섯
    0.55
    ബാ
    0.54
     eléctrico
    0.54
    Ал
    0.54
    お客様
    0.53
    ң
    0.53
    คุณ
    0.52
    دن
    0.52
    Activations Density 0.000%

    No Known Activations