© 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. 105162
    Prev
    Next
    INDEX
    Explanations

    lists, questions, and file headers

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

    whitespace indentation, particularly multiple spaces or tabs used for code or document formatting.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    ଢ
    -1.80
    を選び
    -1.73
     correta
    -1.70
     revisión
    -1.66
    ଝ
    -1.63
     extensão
    -1.62
     recomendación
    -1.56
    ྜ
    -1.56
     maravilh
    -1.54
    鸲
    -1.54
    POSITIVE LOGITS
     of
    2.03
    mathrm
    1.90
    s
    1.70
     not
    1.66
     edifici
    1.59
    g
    1.55
    能
    1.51
    可以
    1.50
     tramont
    1.48
     affatto
    1.47
    Activations Density 0.004%

    No Known Activations