© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 246951
    Prev
    Next
    INDEX
    Explanations

    business, spending, platforms, industrial

    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
    Negative Logits
    贝
    0.49
    养成
    0.48
    我们的
    0.44
     बड़ा
    0.44
    脑
    0.43
     representation
    0.42
    这里的
    0.42
    驻
    0.42
    孟
    0.41
     रुख
    0.41
    POSITIVE LOGITS
    वी
    0.50
     postpon
    0.50
    साठी
    0.48
    utzt
    0.48
    jitter
    0.48
    Semit
    0.47
     fournisseurs
    0.47
     COMPONENTS
    0.46
    page
    0.46
    আনু
    0.46
    Activations Density 0.002%

    No Known Activations