© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 225621
    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
    Negative Logits
    Vaterpolo
    0.49
    Ψ
    0.47
    <0x00>
    0.47
     ditth
    0.47
    ఎఫ్
    0.46
    DataXYZ
    0.46
    Basket
    0.46
    Billing
    0.46
    selValue
    0.46
    employment
    0.46
    POSITIVE LOGITS
     Sometimes
    0.45
     Through
    0.45
     refres
    0.45
    ш
    0.45
     Driving
    0.44
     Refresh
    0.43
     KN
    0.42
     to
    0.42
     Clear
    0.41
    лни
    0.41
    Activations Density 0.008%

    No Known Activations