© 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-65K
    7. 56697
    Prev
    Next
    INDEX
    Explanations

    associated design work

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     flies
    0.43
    ar
    0.42
     gleaming
    0.39
    ²,
    0.39
    {~
    0.38
     Hypertension
    0.38
     eluted
    0.37
     pediat
    0.37
    ub
    0.36
     lspace
    0.36
    POSITIVE LOGITS
    יית
    0.47
    ﻏ
    0.47
    мата
    0.45
     juridique
    0.43
     ؟
    0.43
    καν
    0.43
    culaire
    0.42
    人間の
    0.42
     дорого
    0.41
    ンダ
    0.41
    Activations Density 0.027%

    No Known Activations