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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 95
    Prev
    Next
    INDEX
    Explanations

    contrasting ideas or opinions

    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
    t
    0.65
    jährige
    0.51
     diffé
    0.50
     équip
    0.48
     teint
    0.48
     inhib
    0.47
     เฉ
    0.47
    ministerium
    0.46
     spes
    0.46
     excès
    0.46
    POSITIVE LOGITS
    ಕ
    0.71
    ک
    0.67
    ون
    0.66
    N
    0.60
    ين
    0.59
    W
    0.57
    ಿರ
    0.57
    T
    0.56
    P
    0.56
    ים
    0.55
    Activations Density 0.011%

    No Known Activations