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. 109
    Prev
    Next
    INDEX
    Explanations

    to attain

    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
    ↵
    1.09
    ла
    0.83
    ل
    0.80
    7
    0.74
    7
    0.68
    6
    0.68
    8
    0.66
    л
    0.60
    8
    0.58
    er
    0.57
    POSITIVE LOGITS
     to
    0.90
     an
    0.89
     a
    0.82
     is
    0.81
     be
    0.79
     are
    0.68
     of
    0.66
     the
    0.65
     was
    0.65
     
    0.63
    Activations Density 13.969%

    No Known Activations