© 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. 22-GEMMASCOPE-RES-131K
    7. 26291
    Prev
    Next
    INDEX
    Explanations

    welcome and introductions

    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_22/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
    侷
    -1.11
    COMPLE
    -1.04
    эти
    -1.03
     réflexion
    -1.02
    mäßigen
    -1.01
    картинка
    -0.99
     arrêt
    -0.99
     endommag
    -0.99
     見る
    -0.98
    можно
    -0.98
    POSITIVE LOGITS
     everyone
    1.50
     our
    1.27
    Everyone
    1.19
     everybody
    1.10
    rimos
    1.09
    ाहरण
    1.09
     ставить
    1.08
     يوسف
    1.06
     here
    1.04
     we
    1.02
    Activations Density 0.016%

    No Known Activations