© 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. 7229
    Prev
    Next
    INDEX
    Explanations

    MVP and awards

    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
     into
    -1.29
     to
    -1.24
    ’
    -1.16
     that
    -1.11
    acetic
    -1.08
    hpur
    -1.07
     United
    -1.05
    員
    -1.01
     $__
    -1.01
     its
    -1.01
    POSITIVE LOGITS
    はじめに
    1.24
     racon
    1.21
     aggiunto
    1.19
     mayhem
    1.08
     elettrico
    1.08
     lágrimas
    1.08
    зовать
    1.08
    悵
    1.07
    ﾏ
    1.07
    lenir
    1.07
    Activations Density 0.031%

    No Known Activations