© 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. 145580
    Prev
    Next
    INDEX
    Explanations

    sole of shoe

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

    angle of attack

    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
    ōn
    0.47
     പറ
    0.43
     கண்டு
    0.43
    
    0.43
    tywn
    0.42
    ⵢ
    0.42
    zące
    0.41
    ዬ
    0.41
    鿁
    0.41
    üsü
    0.41
    POSITIVE LOGITS
     sole
    0.54
     KEEP
    0.50
     thank
    0.49
     THANK
    0.49
     accountable
    0.47
    defineProperty
    0.46
     confirm
    0.46
     recruiters
    0.46
     xứng
    0.45
     movie
    0.45
    Activations Density 0.000%

    No Known Activations