© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 788
    Prev
    Next
    INDEX
    Explanations

    specialized topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     milliers
    -1.58
     墊
    -1.56
     우리
    -1.51
     zoude
    -1.48
    えっ
    -1.48
    の準備
    -1.47
     uly
    -1.47
    を選び
    -1.44
     namelijk
    -1.43
     dezelve
    -1.41
    POSITIVE LOGITS
     in
    2.36
     for
    2.34
     vs
    2.33
    :
    2.28
     as
    2.27
     with
    2.23
     on
    2.16
     versus
    2.11
     at
    2.08
     to
    2.02
    Activations Density 0.091%

    No Known Activations