© 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. 36670
    Prev
    Next
    INDEX
    Explanations

    do not touch, disturb, or create

    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
     Governance
    0.44
     governance
    0.39
     Absorption
    0.38
    rolysis
    0.38
     مشر
    0.38
     sectoral
    0.38
     trasmissione
    0.38
    ථ
    0.38
    Absorption
    0.37
    擒
    0.37
    POSITIVE LOGITS
     பய
    0.46
    érico
    0.40
    atus
    0.39
     денег
    0.38
     (€
    0.38
     «
    0.38
     أشهر
    0.37
    aduras
    0.37
     etc
    0.37
     ("",
    0.37
    Activations Density 0.000%

    No Known Activations