© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47677
    Prev
    Next
    INDEX
    Explanations

    bath & card tricks

    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
     HAZ
    -0.73
     Talley
    -0.71
    DLC
    -0.71
    亰
    -0.70
     đề
    -0.68
     Kohler
    -0.68
     тен
    -0.68
    tillo
    -0.68
    ㄦ
    -0.67
    ไข
    -0.67
    POSITIVE LOGITS
     Lush
    1.17
     bath
    1.02
     handmade
    0.94
     Handmade
    0.91
    Bath
    0.85
     shower
    0.84
     Bath
    0.81
    Handmade
    0.81
    interface
    0.80
     lenguas
    0.79
    Activations Density 0.003%

    No Known Activations