© 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. 105896
    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
     teknik
    -1.06
    📐
    -1.03
     '/':
    -1.02
     carrière
    -0.99
    ේ
    -0.98
     nasıl
    -0.98
    cedores
    -0.97
    BURGH
    -0.97
    ✪
    -0.96
    ഃ
    -0.96
    POSITIVE LOGITS
     that
    1.11
     helyzet
    1.03
     overall
    1.03
     which
    0.98
    擷
    0.98
     Which
    0.94
    刪
    0.93
     new
    0.90
    𝗸
    0.90
     who
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.