© 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. 100575
    Prev
    Next
    INDEX
    Explanations

    article titles and headings

    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
     its
    -1.35
     with
    -1.24
    ῾
    -1.16
     by
    -1.16
     our
    -1.12
     improve
    -1.09
    یکس
    -1.08
    æa
    -1.07
     their
    -1.07
     which
    -1.07
    POSITIVE LOGITS
     erken
    1.16
    Dentro
    1.15
    OfWork
    1.13
    daging
    1.09
    \}=\
    1.09
    rafat
    1.07
    saan
    1.06
    স্ট
    1.06
    شنامه
    1.01
     beleid
    1.01
    Activations Density 0.032%

    No Known Activations