© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10372
    Prev
    Next
    INDEX
    Explanations

    proper names and categories

    np_acts-logits-general · gemini-2.5-flash-lite

    word following noun descriptor

    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_40_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
     latter
    0.49
     appunto
    0.44
     എന്നിവ
    0.44
     Etc
    0.43
     etc
    0.41
    ֖
    0.39
    ‍
    0.39
     Và
    0.39
     whatnot
    0.38
     һәм
    0.37
    POSITIVE LOGITS
    -,
    0.83
    、
    0.72
    *,
    0.71
    %、
    0.66
    》、《
    0.65
    ="",
    0.64
    》《
    0.64
    (),
    0.63
    ”、“
    0.62
    」、「
    0.62
    Activations Density 0.862%

    No Known Activations