© 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. 59961
    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
     babes
    -1.11
     vork
    -1.09
     lada
    -1.09
    笅
    -1.07
     territo
    -1.06
    ktionen
    -1.05
    ահ
    -1.04
     menging
    -1.02
    piegel
    -1.02
     مراجع
    -1.00
    POSITIVE LOGITS
     with
    1.11
     on
    0.98
     for
    0.93
     by
    0.90
    琑
    0.86
     also
    0.85
     get
    0.84
     in
    0.84
     foundations
    0.84
     pure
    0.82
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.