© 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. 113439
    Prev
    Next
    INDEX
    Explanations

    headings and titles

    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
     '
    -1.60
    ations
    -1.52
     conoció
    -1.52
    ...)
    -1.52
    X
    -1.51
    ER
    -1.49
    B
    -1.48
    ޚ
    -1.45
     being
    -1.45
    ("")
    -1.44
    POSITIVE LOGITS
     \%$\\
    1.55
    生育
    1.39
     якщо
    1.38
     of
    1.38
    garmin
    1.36
     имеют
    1.35
    甦
    1.33
    boucles
    1.32
     вона
    1.32
    también
    1.32
    Activations Density 0.006%

    No Known Activations