© 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. 80261
    Prev
    Next
    INDEX
    Explanations

    post-punk, deco, incident, incrementally, save

    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
    ם
    0.42
     was
    0.41
     অবশ্য
    0.41
    ախ
    0.41
    둠
    0.40
    荐
    0.40
     warring
    0.39
     communal
    0.38
     astounding
    0.38
    ரி
    0.38
    POSITIVE LOGITS
    werken
    0.43
    klus
    0.43
    wenden
    0.43
     單
    0.43
     ثقاف
    0.42
    រយៈពេល
    0.42
    +}$,
    0.41
     chặn
    0.41
     تل
    0.41
     ژ
    0.40
    Activations Density 0.004%

    No Known Activations