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. 262
    Prev
    Next
    INDEX
    Explanations

    choice is

    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
    z
    0.56
    q
    0.55
    .
    0.54
    re
    0.53
    то
    0.52
    f
    0.50
     ints
    0.49
     sig
    0.49
    و
    0.49
    ور
    0.48
    POSITIVE LOGITS
     величе
    0.50
     بڑھ
    0.48
    tbLabel
    0.48
    詐
    0.48
    Acetoxy
    0.48
    𝕝
    0.48
     xâm
    0.47
     दुरुपयोग
    0.47
     домаћинства
    0.47
     décès
    0.47
    Activations Density 0.000%

    No Known Activations