© 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. 41722
    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
     authoritative
    -0.88
     связанные
    -0.86
    elif
    -0.85
     singen
    -0.85
    ᴀ
    -0.84
    琥
    -0.84
    Ibid
    -0.82
     пише
    -0.82
     були
    -0.81
     hä
    -0.81
    POSITIVE LOGITS
    ´)
    1.09
    gaw
    1.05
     pojaw
    1.00
     among
    0.97
    神色
    0.94
     and
    0.94
     seluruh
    0.94
    cunt
    0.94
    georg
    0.93
     sypial
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.