© 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. 110776
    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
     pasirink
    -1.16
     américains
    -1.12
    filtre
    -1.07
     européens
    -1.05
    onymus
    -1.02
     hábit
    -1.00
     ivelany
    -0.99
     surabaya
    -0.96
    chose
    -0.96
     gikk
    -0.94
    POSITIVE LOGITS
    ↵↵
    0.96
     it
    0.92
     and
    0.88
    O
    0.84
     when
    0.84
     methamphetamine
    0.83
     nai
    0.82
     your
    0.82
     secas
    0.81
    зва
    0.81
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.