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. 366
    Prev
    Next
    INDEX
    Explanations

    first-person realizations and thoughts

    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
     convexo
    0.56
    નુ
    0.56
    ր
    0.56
    arag
    0.56
    на
    0.55
     couronne
    0.55
     هایی
    0.55
     extraordinaire
    0.54
    ibilités
    0.54
    казыва
    0.53
    POSITIVE LOGITS
    _
    0.66
    ählten
    0.61
    X
    0.60
    <0x0D>
    0.57
    							
    0.55
     spear
    0.55
    5
    0.55
     implements
    0.53
    এক
    0.53
    ৫
    0.53
    Activations Density 0.002%

    No Known Activations