© 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. 22-GEMMASCOPE-RES-131K
    7. 28548
    Prev
    Next
    INDEX
    Explanations

    places and platforms

    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_22/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
     كه
    -1.13
    을
    -1.00
    érfi
    -0.99
     that
    -0.96
    लाई
    -0.93
    或者
    -0.93
    ulitis
    -0.90
    明日は
    -0.90
    になれば
    -0.89
    7
    -0.88
    POSITIVE LOGITS
     by
    1.24
    álás
    1.02
    њи
    1.01
     μας
    1.00
     الصحة
    0.98
     as
    0.97
    ?}",
    0.94
    出版年
    0.94
     rique
    0.94
     Municipalidad
    0.93
    Activations Density 0.064%

    No Known Activations