© 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. 130270
    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
     if
    -1.38
     while
    -1.10
    ulauan
    -0.96
    rimas
    -0.94
    rijke
    -0.93
     szob
    -0.92
    beda
    -0.91
    као
    -0.91
    maksi
    -0.90
     آشپزخانه
    -0.90
    POSITIVE LOGITS
     aceste
    1.08
     المكتبه
    1.02
    im
    1.02
     estos
    1.00
     necesarios
    1.00
    u
    0.98
    os
    0.98
    ier
    0.98
    ou
    0.98
    IM
    0.97
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.