© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84545
    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
     OLIVE
    -1.09
     garantiza
    -1.09
    ඍ
    -1.05
    ほとん
    -1.04
    כּ
    -1.02
     soooo
    -1.02
     actualizada
    -1.02
     femininas
    -1.01
     każdej
    -1.00
    
    -1.00
    POSITIVE LOGITS
     with
    1.34
     for
    1.26
     without
    1.24
     in
    1.16
    ↵
    1.15
     an
    1.13
     some
    1.13
     //
    1.07
     when
    1.05
     lista
    1.03
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.