© 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. 66201
    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
    ̷
    -1.06
     terem
    -1.04
     чего
    -0.98
    颁
    -0.93
     trasero
    -0.93
     Hinblick
    -0.91
    ̩
    -0.91
    NEED
    -0.90
    イチ
    -0.90
     かわいい
    -0.89
    POSITIVE LOGITS
     perubahan
    1.10
     that
    1.07
    &
    1.05
    ℬ
    1.05
    verläs
    1.02
    呓
    1.02
     obicei
    0.99
     μπορεί
    0.96
    ℛ
    0.95
     zwykle
    0.95
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.