© 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. 84136
    Prev
    Next
    INDEX
    Explanations

    old ways

    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
    ほんとに
    -0.97
    RESULT
    -0.89
    よろしくお願い
    -0.88
    耸
    -0.88
     скром
    -0.88
     Klage
    -0.88
    将其
    -0.87
    顛
    -0.87
    CDCl
    -0.87
    both
    -0.87
    POSITIVE LOGITS
    了
    1.00
     paysages
    0.93
     vaguely
    0.93
     khaki
    0.92
     lèvres
    0.90
     Conventions
    0.88
     είχε
    0.88
     Ghetto
    0.88
    thorne
    0.88
    alcool
    0.87
    Activations Density 0.014%

    No Known Activations