© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14909
    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
     This
    -1.12
    :...
    -1.11
    ));
    -1.10
    )));
    -1.09
     cuando
    -1.02
     while
    -1.02
    𖥧
    -1.02
     kilometr
    -1.00
    )),
    -1.00
     in
    -0.98
    POSITIVE LOGITS
    蘩
    1.13
     شکر
    1.13
    тися
    1.13
     黑色
    1.11
     égal
    1.09
     Ответить
    1.06
    veloppe
    1.05
     vó
    1.04
     quitte
    1.03
    ՜
    1.03
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.