© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 34120
    Prev
    Next
    INDEX
    Explanations

    you shave

    np_acts-logits-general · gemini-2.5-flash-lite

    capsaicin and tea

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    当中
    0.47
     ប៉ុ
    0.47
    形态
    0.46
    っていう
    0.46
    若
    0.46
    \;
    0.46
    选取
    0.46
     канторы
    0.45
    
    0.45
     ถ้า
    0.44
    POSITIVE LOGITS
    0.49
     Sapp
    0.47
     Harry
    0.46
     Cornwall
    0.45
     Karan
    0.43
     donation
    0.42
    चीन
    0.42
     TAR
    0.42
     Suzuki
    0.41
     donated
    0.40
    Activations Density 0.000%

    No Known Activations