© 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. 33476
    Prev
    Next
    INDEX
    Explanations

    invasion of

    np_acts-logits-general · gemini-2.5-flash-lite

    whitespace and indentation in programming code.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     zpra
    -0.74
    ึ้น
    -0.74
    aktor
    -0.73
    干什么
    -0.71
     LANE
    -0.69
     térmica
    -0.69
    Materiál
    -0.69
     Система
    -0.67
    Prí
    -0.67
     BOARD
    -0.66
    POSITIVE LOGITS
    jana
    0.72
    zk
    0.69
    uri
    0.66
    íqu
    0.66
     quid
    0.66
     Enlarged
    0.65
     సౌకర్య
    0.65
     न
    0.64
    bots
    0.63
     Enlarge
    0.63
    Activations Density 0.077%

    No Known Activations