© 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-16K
    7. 7737
    Prev
    Next
    INDEX
    Explanations

    code identifiers and operators

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     untreated
    0.45
     nonlocal
    0.39
     Challenges
    0.38
     parar
    0.37
     deliberately
    0.37
     sho
    0.37
    inoa
    0.37
    ረ
    0.36
    ś
    0.36
     succeeds
    0.36
    POSITIVE LOGITS
    ->$
    0.49
    "?>
    0.46
    㴬
    0.45
    =$
    0.43
    ,$
    0.43
    ">$
    0.43
    ?$
    0.42
    [$
    0.42
    Orient
    0.40
    PlistBuddy
    0.39
    Activations Density 0.103%

    No Known Activations