© 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. 226100
    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
    ⿹
    0.50
    ampuan
    0.48
     ಪುಟ
    0.47
     {}>,
    0.46
     интернет
    0.46
    𝙻
    0.44
     चट
    0.43
    wayat
    0.43
     சாப்பி
    0.43
    UNIVERSITY
    0.42
    POSITIVE LOGITS
    1
    0.52
     Theft
    0.47
     Billion
    0.46
     engineer
    0.44
    खार
    0.43
    ફે
    0.43
     세율
    0.43
    ف
    0.41
     Prevent
    0.41
     Augmented
    0.41
    Activations Density 0.008%

    No Known Activations