© 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. 39625
    Prev
    Next
    INDEX
    Explanations

    code structures and data parsing

    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
     Spisak
    -0.98
     two
    -0.96
     etc
    -0.92
    two
    -0.92
    the
    -0.90
    and
    -0.85
    мки
    -0.85
    etc
    -0.85
    Two
    -0.85
    The
    -0.85
    POSITIVE LOGITS
    同上
    1.43
     materiais
    1.16
     mirip
    1.06
    Katalog
    1.01
    NACIONAL
    0.99
    エット
    0.97
    躡
    0.96
    なのでしょう
    0.95
    Rasp
    0.94
    carus
    0.94
    Activations Density 0.010%

    No Known Activations