© 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. 26146
    Prev
    Next
    INDEX
    Explanations

    names and places

    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
     at
    -1.70
     where
    -1.42
    thirds
    -1.34
    ！！！！！
    -1.30
     illustratie
    -1.28
     without
    -1.27
     whose
    -1.25
     which
    -1.21
     with
    -1.21
    ！(
    -1.20
    POSITIVE LOGITS
     groote
    1.27
     amazing
    1.23
    斯基
    1.23
    …(
    1.16
    coration
    1.16
    事は
    1.09
    ほら
    1.09
    んですが
    1.09
     gewi
    1.08
     agujero
    1.08
    Activations Density 0.092%

    No Known Activations