© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19629
    Prev
    Next
    INDEX
    Explanations

    compound names

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

    company and organization names.

    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_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
    鯷
    -1.75
     détruire
    -1.59
    还不错
    -1.56
    ༈
    -1.55
    Otras
    -1.50
     bénévol
    -1.48
     trouxe
    -1.48
     alza
    -1.47
     conviene
    -1.47
     consommer
    -1.46
    POSITIVE LOGITS
     those
    2.13
     and
    2.08
     for
    1.88
     They
    1.87
     not
    1.87
     of
    1.81
     That
    1.73
     both
    1.68
     their
    1.62
     but
    1.60
    Activations Density 0.131%

    No Known Activations