© 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. 35002
    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
    が
    -2.23
     in
    -2.22
    だが
    -1.95
    を
    -1.77
    もある
    -1.77
    があります
    -1.77
    など
    -1.76
    も
    -1.73
    子が
    -1.73
    そして
    -1.68
    POSITIVE LOGITS
    ちょこ
    2.27
    為に
    2.20
    様な
    2.16
    ＊＊＊＊
    2.06
    感じで
    2.06
    ままで
    2.03
    久し
    2.02
    ようで
    1.98
    感じが
    1.96
    ところに
    1.95
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.