© 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. 75999
    Prev
    Next
    INDEX
    Explanations

    swimming pools

    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
     กระ
    -0.86
    .'</
    -0.81
    ős
    -0.79
    ();
    -0.77
    гаре
    -0.76
    èm
    -0.76
    nment
    -0.76
    .}\
    -0.75
    bí
    -0.75
    >();
    -0.75
    POSITIVE LOGITS
     pool
    1.41
     swimmers
    1.23
     Pool
    1.19
     Swimming
    1.17
     swimming
    1.11
     algae
    1.08
     Swim
    1.02
    pool
    1.02
    Pool
    1.01
     swim
    0.99
    Activations Density 0.010%

    No Known Activations