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. 179
    Prev
    Next
    INDEX
    Explanations

    famous people's 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
    as
    0.57
    u
    0.49
    os
    0.48
    l
    0.47
    t
    0.46
    f
    0.43
    on
    0.42
    ul
    0.42
    ن
    0.42
    ar
    0.41
    POSITIVE LOGITS
     be
    0.50
     biographer
    0.42
     an
    0.40
     can
    0.38
     in
    0.37
     politician
    0.37
     directeur
    0.37
    ции
    0.37
     zu
    0.36
     reluctantly
    0.36
    Activations Density 1.025%

    No Known Activations