© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103589
    Prev
    Next
    INDEX
    Explanations

    Powerful Partnerships

    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
     then
    -2.09
     after
    -1.41
     Stornier
    -1.38
    ApJ
    -1.37
     other
    -1.37
     as
    -1.35
     latter
    -1.33
     called
    -1.31
    ichtete
    -1.29
    之时
    -1.27
    POSITIVE LOGITS
     Ответить
    1.52
    がなく
    1.52
     normaal
    1.51
    妡
    1.49
    stones
    1.48
     tromper
    1.47
    ⩽
    1.46
     alltid
    1.45
    ⩾
    1.45
    time
    1.43
    Activations Density 0.003%

    No Known Activations