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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11696
    Prev
    Next
    INDEX
    Explanations

    figure/reference/with context

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

    code syntax and math expressions

    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
    withtag
    0.43
     ("
    0.41
    合併
    0.40
     -"
    0.39
    pinimg
    0.39
    )(-
    0.39
    =('
    0.38
    合并
    0.38
     merger
    0.38
    ">⁡</
    0.38
    POSITIVE LOGITS
     [
    3.08
    [
    2.56
     $[
    2.34
     [_
    2.13
    }[
    2.02
     \[
    2.00
     }[
    1.98
     [\
    1.91
     [$
    1.91
    $[
    1.90
    Activations Density 0.128%

    No Known Activations