© 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. 24536
    Prev
    Next
    INDEX
    Explanations

    code docstring parameter definitions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     evidently
    0.42
    年月日
    0.39
     @
    0.39
     simply
    0.39
     affaires
    0.39
     fairies
    0.38
     weren
    0.38
     Didn
    0.38
     $-\
    0.37
     జాగ్ర
    0.37
    POSITIVE LOGITS
    푝
    0.42
    妷
    0.38
    Processing
    0.38
     voglia
    0.37
    |}
    0.37
    **************
    0.37
     procesamiento
    0.36
    들의
    0.36
    ность
    0.36
    Coluna
    0.36
    Activations Density 0.003%

    No Known Activations