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. 76
    Prev
    Next
    INDEX
    Explanations

    your own, hospital, package mix

    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
    빗
    0.49
    び
    0.49
    arii
    0.48
    iann
    0.48
    esc
    0.48
     d
    0.46
     pueden
    0.45
    も
    0.45
    emore
    0.45
    burg
    0.45
    POSITIVE LOGITS
     magnetometer
    0.63
     тесто
    0.62
    ئه
    0.58
     testen
    0.58
    ynomial
    0.57
    рда
    0.53
     magnetite
    0.52
    цер
    0.52
     elektromagnet
    0.52
    ئن
    0.51
    Activations Density 0.001%

    No Known Activations