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. 112
    Prev
    Next
    INDEX
    Explanations

    because the

    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
     drugi
    0.53
     канторы
    0.50
    ૧
    0.48
     கெல்வின்
    0.46
     patru
    0.46
    I
    0.45
     ন্যূনতম
    0.45
     têm
    0.45
    )،
    0.45
     gült
    0.45
    POSITIVE LOGITS
    ,
    0.77
    ↵↵
    0.63
    ↵
    0.62
    t
    0.54
    '
    0.50
    因为
    0.47
    us
    0.47
     because
    0.45
    因为它
    0.42
    ات
    0.41
    Activations Density 7.461%

    No Known Activations