© 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. 128425
    Prev
    Next
    INDEX
    Explanations

    decades

    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
     グラス
    -1.23
    があるので
    -1.22
     promesse
    -1.21
    канал
    -1.18
    もあるので
    -1.17
    瓒
    -1.16
     podmín
    -1.15
    ೞ
    -1.13
    你们的
    -1.13
    nemies
    -1.12
    POSITIVE LOGITS
     and
    1.47
     latter
    1.18
    s
    1.14
     ensuing
    1.11
     At
    1.09
     &
    1.09
    acuzzi
    1.09
     sanoo
    1.09
     nazionale
    1.05
    C
    1.05
    Activations Density 0.027%

    No Known Activations