© 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. 34-GEMMASCOPE-RES-131K
    7. 84920
    Prev
    Next
    INDEX
    Explanations

    Bass or Bas, followed by capitalized words

    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_34/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
     состо
    -0.81
    大さじ
    -0.77
     آذ
    -0.77
     katt
    -0.75
    atuur
    -0.75
     únicos
    -0.74
    لیل
    -0.74
     lógica
    -0.74
    λεκ
    -0.74
    áis
    -0.73
    POSITIVE LOGITS
     Nachmittag
    0.75
    خره
    0.73
    IDADES
    0.73
    ìa
    0.72
    Tone
    0.72
     berkenaan
    0.71
     welt
    0.71
     await
    0.71
    スズキ
    0.71
    Erosion
    0.69
    Activations Density 0.037%

    No Known Activations