© 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. 260995
    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
     quatro
    0.54
    ן
    0.50
     três
    0.48
    硣
    0.47
     மூன்று
    0.46
     ನಾಲ್
    0.45
     reconhe
    0.45
     astonishing
    0.45
     ensinar
    0.44
    quatre
    0.44
    POSITIVE LOGITS
    vény
    0.48
    ęt
    0.45
    윅
    0.45
    assignmentItems
    0.43
    ถือ
    0.43
     Сак
    0.43
    🙋
    0.42
    ्यूट
    0.42
    最后一个
    0.42
    았다
    0.41
    Activations Density 0.000%

    No Known Activations