© 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. 10-GEMMASCOPE-RES-131K
    7. 103524
    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
     și
    -3.19
    ᕱ
    -2.88
     और
    -2.78
    และ
    -2.70
     моя
    -2.63
    神
    -2.61
    他的
    -2.58
    ,"
    -2.55
    性和
    -2.55
    髕
    -2.53
    POSITIVE LOGITS
     By
    2.55
     in
    2.50
    2
    2.41
     For
    2.23
    \
    2.22
     able
    2.20
    на
    2.19
        
    2.14
    This
    2.13
     Someone
    2.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.