© 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. 9256
    Prev
    Next
    INDEX
    Explanations

    reporting future events

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     reimag
    0.40
     rebuke
    0.38
     (“
    0.36
     voilà
    0.34
     inspires
    0.34
     resonate
    0.34
     argu
    0.33
    ！
    0.33
     defies
    0.33
    ête
    0.33
    POSITIVE LOGITS
    据悉
    0.47
     الخدمات
    0.39
    한편
    0.38
     خواهد
    0.37
     Plans
    0.37
     PLANS
    0.37
     Presently
    0.37
     Services
    0.35
    其他的
    0.35
     STORE
    0.35
    Activations Density 0.001%

    No Known Activations