© 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. 14442
    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
     rano
    -0.97
    ＄
    -0.94
     définir
    -0.94
     Erlebn
    -0.91
    beers
    -0.91
    薬品
    -0.90
    сете
    -0.88
    Seriously
    -0.88
     magnético
    -0.88
    сет
    -0.87
    POSITIVE LOGITS
     навіть
    1.29
     even
    1.07
    甚至
    1.00
     sogar
    0.93
     даже
    0.93
     thậm
    0.92
    いえば
    0.91
     buen
    0.91
     هذه
    0.90
    even
    0.87
    Activations Density 0.000%

    No Known Activations