© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39332
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     where
    -1.27
     are
    -1.16
     and
    -1.15
     able
    -1.09
     jeste
    -1.08
    ردد
    -1.08
    Ƃ
    -1.08
     just
    -1.06
    |};
    -1.04
     efectiva
    -0.93
    POSITIVE LOGITS
    ⅙
    1.16
     FACT
    1.16
    ₤
    1.12
     \#
    1.09
    ⅕
    1.09
    ʹ
    1.08
    führende
    1.05
    ⅜
    1.05
    まぁ
    1.04
    ffindor
    1.04
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.