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-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 3314
    Prev
    Next
    INDEX
    Explanations

    still, uncertainty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    മാക
    0.74
    ISIONS
    0.73
    <ul>
    0.70
    aculate
    0.70
    iflor
    0.69
    icula
    0.69
    lemens
    0.69
     createCanvas
    0.68
    idenza
    0.67
    璁
    0.66
    POSITIVE LOGITS
     still
    6.01
    still
    5.21
     Still
    5.12
    Still
    5.01
    仍然
    4.79
     STILL
    4.73
    仍
    4.46
     vẫn
    4.46
    依然
    4.41
     masih
    4.40
    Activations Density 1.116%

    No Known Activations