© 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. 40-GEMMASCOPE-2-RES-262K
    7. 12894
    Prev
    Next
    INDEX
    Explanations

    fast forward and patch

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     copie
    0.42
    ịn
    0.41
     gooey
    0.41
     copies
    0.40
    els
    0.39
     games
    0.38
    Multimedia
    0.38
    杭
    0.38
     neuer
    0.37
     malware
    0.37
    POSITIVE LOGITS
     שב
    0.40
    量を
    0.40
    ुभ
    0.39
     যতই
    0.39
    ਭ
    0.38
     дү
    0.38
     terb
    0.37
     penso
    0.37
     }//
    0.37
    シス
    0.37
    Activations Density 0.000%

    No Known Activations