© 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. 258696
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ની
    0.64
    ໋
    0.60
     như
    0.58
    ers
    0.57
    기
    0.57
    
    0.57
    ,_
    0.57
    이었다
    0.56
    の場合は
    0.55
    の中心
    0.55
    POSITIVE LOGITS
    i
    0.42
     škol
    0.40
    pop
    0.40
     scorsa
    0.39
    ودة
    0.39
    olius
    0.38
    teste
    0.37
    Teste
    0.37
    闂
    0.37
    ុក
    0.37
    Activations Density 0.000%

    No Known Activations