© 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. 22191
    Prev
    Next
    INDEX
    Explanations

    support for research and causes

    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
     endearing
    -1.36
     apaixon
    -1.34
     consulté
    -1.33
     It
    -1.27
     their
    -1.26
    ▿
    -1.26
    をもら
    -1.25
     aptly
    -1.23
    なくなった
    -1.22
     freaking
    -1.21
    POSITIVE LOGITS
    konos
    1.53
    遢
    1.50
     можуть
    1.38
    geſ
    1.36
    questa
    1.28
    umerable
    1.28
     setelah
    1.26
     МВД
    1.25
     веществ
    1.23
    dieux
    1.23
    Activations Density 0.026%

    No Known Activations