© 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. 70197
    Prev
    Next
    INDEX
    Explanations

    court documents

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ἵ
    -0.84
     [''
    -0.83
    拷贝
    -0.82
    Какой
    -0.82
    Funcion
    -0.81
     DAL
    -0.79
     lager
    -0.79
    Интер
    -0.79
     ladd
    -0.78
    Мор
    -0.77
    POSITIVE LOGITS
    icot
    0.91
     אפ
    0.88
     records
    0.87
     إ
    0.87
     checklist
    0.84
     concludes
    0.83
    arised
    0.81
     שט
    0.79
    最後まで
    0.78
    oner
    0.78
    Activations Density 0.020%

    No Known Activations