© 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. 44908
    Prev
    Next
    INDEX
    Explanations

    dub followed by suffixes

    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
     маленьких
    -2.91
    即便是
    -2.86
    ſu
    -2.75
    谖
    -2.73
     verwendeten
    -2.50
     entsprechen
    -2.41
    ︲
    -2.39
     mesmos
    -2.38
     también
    -2.36
     могут
    -2.34
    POSITIVE LOGITS
    ’
    3.17
    d
    2.75
    ྂ
    2.66
    iste
    2.55
    ၞ
    2.55
    b
    2.38
    \
    2.30
     improbable
    2.28
     dalam
    2.27
    a
    2.25
    Activations Density 0.003%

    No Known Activations