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-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 233
    Prev
    Next
    INDEX
    Explanations

    plain bottle trainer names

    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
     caos
    0.54
     హైదర్
    0.50
    .');
    0.49
    陴
    0.46
    だい
    0.46
    strates
    0.46
    .';
    0.45
    。)
    0.45
    .')
    0.45
    葢
    0.44
    POSITIVE LOGITS
     mengan
    0.51
    ם
    0.51
     kidn
    0.47
    outlined
    0.47
     rescue
    0.46
    y
    0.46
    ുന്നു
    0.45
    p
    0.45
     superimposed
    0.44
     tid
    0.44
    Activations Density 0.000%

    No Known Activations