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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 123
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    ת
    0.55
    -
    0.46
    :
    0.45
    고
    0.45
    る
    0.43
     diaria
    0.39
    त
    0.39
    కు
    0.39
     prestazioni
    0.38
    ت
    0.37
    POSITIVE LOGITS
    ۹
    0.44
    ल्पनिक
    0.42
     be
    0.39
    of
    0.38
    for
    0.36
    چه
    0.36
    creat
    0.36
    is
    0.35
    पहरण
    0.35
    was
    0.34
    Activations Density 0.000%

    No Known Activations