© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112567
    Prev
    Next
    INDEX
    Explanations

    not followed by negation

    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_10/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
    Different
    -1.58
    However
    -1.55
    おはよう
    -1.54
    Seperti
    -1.48
    !」
    -1.45
    ―――
    -1.45
     插图
    -1.45
     墊
    -1.43
     抠
    -1.43
    ごちそう
    -1.41
    POSITIVE LOGITS
     "
    1.95
     “
    1.61
     and
    1.57
     then
    1.55
     two
    1.53
     three
    1.51
     four
    1.43
           
    1.41
     cuyo
    1.41
     first
    1.34
    Activations Density 0.057%

    No Known Activations