© 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. 40052
    Prev
    Next
    INDEX
    Explanations

    tableware and dining items

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    icoot
    -1.60
    綃
    -1.52
    Distinctions
    -1.46
     of
    -1.45
    喼
    -1.41
    GRAPHY
    -1.41
    tività
    -1.40
     menyen
    -1.39
    3
    -1.34
    蹇
    -1.34
    POSITIVE LOGITS
     waarbij
    1.38
    obtained
    1.37
    ';
    1.35
     haciendo
    1.34
    谙
    1.29
     особенно
    1.27
     obtenido
    1.27
     cai
    1.24
    whose
    1.23
     waarmee
    1.23
    Activations Density 0.009%

    No Known Activations