© 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. 69868
    Prev
    Next
    INDEX
    Explanations

    awards, best, company, world, ethical, rated, best managed

    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
    itaries
    -0.82
    neous
    -0.80
     Witherspoon
    -0.75
    ?&
    -0.73
    ắt
    -0.73
     kỹ
    -0.72
     respirar
    -0.72
    疥
    -0.71
    弊
    -0.70
    chieben
    -0.70
    POSITIVE LOGITS
     Brand
    0.93
     Frost
    0.85
     preferred
    0.85
     awarded
    0.85
     trusted
    0.83
     SUV
    0.81
     brands
    0.80
    Brand
    0.80
     вру
    0.78
     büyü
    0.77
    Activations Density 0.015%

    No Known Activations