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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 479
    Prev
    Next
    INDEX
    Explanations

    apostrophes and quotes

    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
     The
    0.74
    o
    0.71
    ے
    0.70
    ى
    0.70
     ছিলেন
    0.65
    <h3>
    0.65
     Kyrgyz
    0.65
    ב
    0.64
     
    0.63
    The
    0.62
    POSITIVE LOGITS
    ية
    0.73
    可能會
    0.61
    rire
    0.60
     యొక్క
    0.60
    <0x80>
    0.59
    ruits
    0.59
    ’
    0.59
    يمق
    0.57
    spiration
    0.57
    abilités
    0.57
    Activations Density 0.006%

    No Known Activations