© 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. 25485
    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
     qualquer
    -1.00
     wherever
    -1.00
     setiap
    -0.95
     that
    -0.93
     berbagai
    -0.93
     selalu
    -0.93
     gravidez
    -0.91
    それぞれの
    -0.91
    ochim
    -0.89
    ững
    -0.89
    POSITIVE LOGITS
    owany
    1.02
    化为
    0.98
     oeuvre
    0.96
    荧
    0.91
    𝘩
    0.90
    ських
    0.87
    0.87
     изготов
    0.83
    <>();
    0.82
     maman
    0.82
    Activations Density 0.000%
    No Known Activations
    This feature has no known activations.