© 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. 21691
    Prev
    Next
    INDEX
    Explanations

    found, append, again, structures, for, with, something, lot

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ﺤ
    0.61
    தெ
    0.54
    ெ
    0.51
    எ
    0.51
    бі
    0.50
    உ
    0.50
    ૫
    0.50
    フェ
    0.50
    қ
    0.50
    у
    0.50
    POSITIVE LOGITS
    adrat
    0.43
     fax
    0.41
     beschik
    0.40
    isting
    0.39
     muit
    0.39
     了
    0.38
    了我
    0.38
     رم
    0.38
     inesper
    0.37
     tantalum
    0.37
    Activations Density 0.002%

    No Known Activations