© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 226370
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    й
    0.53
    ğer
    0.49
    летия
    0.47
    🥂
    0.47
    🧪
    0.47
    ми
    0.46
    ковать
    0.46
     utilisés
    0.45
    Encoding
    0.45
    娱
    0.44
    POSITIVE LOGITS
     protein
    0.46
     glial
    0.44
     സംഭവ
    0.43
     e
    0.43
     occur
    0.43
    ISH
    0.43
     FINAL
    0.42
     phrases
    0.42
     appear
    0.42
     emoticon
    0.42
    Activations Density 0.004%

    No Known Activations