© 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. 137772
    Prev
    Next
    INDEX
    Explanations

    descriptive concepts

    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
     Disorder
    0.44
     Changel
    0.41
     Disorders
    0.39
     忄
    0.39
     free
    0.38
     bel
    0.37
    Entry
    0.37
     Entry
    0.37
    勬
    0.37
     ministries
    0.37
    POSITIVE LOGITS
    期货
    0.42
    दिष्ट
    0.41
    万美元
    0.40
     gefähr
    0.38
     måste
    0.37
     Qxh
    0.37
    vir
    0.37
     редакти
    0.36
    тились
    0.36
    錤
    0.36
    Activations Density 0.000%

    No Known Activations