© 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. 85737
    Prev
    Next
    INDEX
    Explanations

    legal terms

    np_acts-logits-general · gemini-2.5-flash-lite

    conditions or outcomes

    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
    ثمار
    0.44
    Good
    0.43
    ্লাহ
    0.43
    青春
    0.43
    奇
    0.41
    үү
    0.40
    ="
    0.39
     شر
    0.38
     chất
    0.38
    НИЕ
    0.38
    POSITIVE LOGITS
     Chambre
    0.56
    again
    0.55
     ಅರ್ಜಿ
    0.55
    gan
    0.55
    vene
    0.54
    usa
    0.52
     Sait
    0.52
     auxqu
    0.52
    bind
    0.51
     abbia
    0.51
    Activations Density 0.001%

    No Known Activations