© 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. 12137
    Prev
    Next
    INDEX
    Explanations

    political parties, sports teams, legal cases, environmental issues, viruses

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

    names of sports teams, political parties, and organizations.

    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
    $
    -2.19
     этого
    -1.78
    i
    -1.68
    h
    -1.60
    *
    -1.55
    //
    -1.45
     этот
    -1.45
    )
    -1.43
    ve
    -1.41
    #
    -1.41
    POSITIVE LOGITS
     Proceeding
    1.59
     powinna
    1.47
    yons
    1.47
    饧
    1.45
    menea
    1.45
    .’
    1.45
    ıdır
    1.45
    gway
    1.41
     to
    1.40
     Bereichen
    1.40
    Activations Density 0.002%

    No Known Activations