© 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. 72905
    Prev
    Next
    INDEX
    Explanations

    don't, didn't

    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_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
    瓛
    -1.63
    вара
    -1.62
    鎘
    -1.58
    趿
    -1.57
     آن‌ها
    -1.57
     bricola
    -1.52
     parfois
    -1.43
    Ꭸ
    -1.41
     fixa
    -1.41
    iforme
    -1.41
    POSITIVE LOGITS
     and
    1.73
    /
    1.56
     other
    1.52
    gencias
    1.50
     various
    1.49
     those
    1.47
     leichte
    1.45
     people
    1.43
     burbujas
    1.41
    地域の
    1.38
    Activations Density 0.062%

    No Known Activations