© 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. 128729
    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
    lrrrr
    -1.23
     их
    -1.20
     their
    -1.17
    kadang
    -1.17
    cautions
    -1.12
    izzate
    -1.09
    mbps
    -1.09
    URDAY
    -1.09
    為に
    -1.06
    corrhi
    -1.04
    POSITIVE LOGITS
    我們
    1.10
    achieve
    1.09
    我们
    1.04
    ENVIRONMENTAL
    1.04
    と思ったら
    1.03
    もしか
    1.03
    ׳
    1.03
    かなぁ
    1.02
     שלנו
    0.99
    chuhe
    0.98
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.