© 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. 12328
    Prev
    Next
    INDEX
    Explanations

    entity names followed by descriptions

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

    legal documents with standard formatting, especially court filings.

    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
    langsung
    -1.68
    でしたか
    -1.57
     stratég
    -1.54
    珦
    -1.54
     verwijderen
    -1.52
    tituts
    -1.51
    harusnya
    -1.49
     ebenfalls
    -1.48
     dinosaurios
    -1.41
     pieles
    -1.38
    POSITIVE LOGITS
     is
    2.44
     has
    1.88
     because
    1.41
    %
    1.40
    2
    1.40
     are
    1.35
    ～～
    1.27
    4
    1.27
    when
    1.26
     keď
    1.26
    Activations Density 0.036%

    No Known Activations