© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 226746
    Prev
    Next
    INDEX
    Explanations

    SharePoint technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    様々な
    0.46
     कसो
    0.46
    まい
    0.43
    ಟ್ಟ
    0.42
    mok
    0.42
    ARIOS
    0.42
    כי
    0.42
    נע
    0.41
    м
    0.41
    buah
    0.40
    POSITIVE LOGITS
     Scripture
    0.49
     dítě
    0.45
     orijinal
    0.44
    赝
    0.44
    精灵
    0.43
     euh
    0.43
     alınd
    0.43
    帘
    0.43
     northward
    0.42
     lied
    0.42
    Activations Density 0.001%

    No Known Activations