© 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. 130153
    Prev
    Next
    INDEX
    Explanations

    potions and forgotten alchemy

    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
     mined
    0.43
     Europa
    0.41
    i
    0.40
    lit
    0.39
     suffer
    0.38
    home
    0.38
    zin
    0.38
    floating
    0.38
     पिला
    0.37
     shadow
    0.37
    POSITIVE LOGITS
    Carousel
    0.39
     failures
    0.38
    厥
    0.38
     సమస్య
    0.38
    ⤵
    0.37
    Logic
    0.37
    期限
    0.37
    WinCounter
    0.37
     manifesting
    0.37
    featur
    0.37
    Activations Density 0.001%

    No Known Activations