© 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. 35330
    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
     márm
    -1.11
     οποίο
    -1.07
     яке
    -1.03
    itares
    -1.02
    úgó
    -1.02
     wyposa
    -0.99
     burbu
    -0.98
    よろしくお願いいたします
    -0.98
    UTIVE
    -0.98
    aliers
    -0.98
    POSITIVE LOGITS
    U
    1.10
     plenty
    1.07
     downloaden
    0.94
     比
    0.93
     those
    0.93
     disponibilité
    0.92
     incite
    0.92
    )'
    0.91
     パイ
    0.91
     heral
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.