© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 3594
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    狁
    -1.06
    鹟
    -1.03
    in
    -0.97
    ण्ड
    -0.95
     schützen
    -0.95
    ︓
    -0.93
    fully
    -0.92
     トレ
    -0.90
    Norfolk
    -0.89
    ált
    -0.88
    POSITIVE LOGITS
     affluent
    1.02
    tuce
    0.88
    dzić
    0.87
     outreach
    0.86
    hach
    0.85
     Fä
    0.85
     Tonnen
    0.84
     and
    0.84
    äische
    0.84
    ements
    0.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.