© 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. 65308
    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
     antik
    -1.23
     октября
    -1.16
    chemise
    -1.13
    に入れ
    -1.09
     المدن
    -1.09
    pretation
    -1.08
     our
    -1.08
    に似
    -1.05
    iato
    -1.05
    感じが
    -1.03
    POSITIVE LOGITS
    その
    1.09
    そんな
    1.09
    żna
    1.06
     такого
    1.05
    توضیحات
    1.03
     ARISING
    1.03
    استفاده
    1.02
    ).
    1.00
    今まで
    0.96
    これは
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.