© 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. 33702
    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
     Bedürf
    -1.22
     cousin
    -1.13
    ߠ
    -1.09
     utilisées
    -1.06
     usada
    -1.03
     Fähig
    -1.03
     récemment
    -1.03
    mainwindow
    -1.02
    lllllllll
    -1.02
     leaning
    -1.00
    POSITIVE LOGITS
     are
    1.00
     UI
    0.98
    minyak
    0.95
    ếm
    0.95
     jsou
    0.92
    praxis
    0.92
     these
    0.91
    agents
    0.91
     }^{*}
    0.90
     iglesia
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.