© 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. 112749
    Prev
    Next
    INDEX
    Explanations

    scan followed by term

    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
    鶫
    -2.44
    ים
    -2.38
     คือ
    -2.34
     髪型
    -2.28
    шена
    -2.27
    cription
    -2.25
     皇族
    -2.22
    킁
    -2.22
    ⁛
    -2.17
    훙
    -2.16
    POSITIVE LOGITS
    ?
    3.05
    of
    2.67
    $
    2.48
    able
    2.34
    {
    2.30
     convincing
    2.19
    in
    2.17
    釙
    2.09
    :
    2.09
    ))
    2.06
    Activations Density 0.012%

    No Known Activations