© 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. 213470
    Prev
    Next
    INDEX
    Explanations

    wall street, restaurant with

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

    reflects differences

    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
    伟大
    0.48
     держави
    0.44
    혹
    0.43
     Doncaster
    0.42
     republic
    0.41
     République
    0.41
     კ
    0.41
     구현
    0.41
     деклара
    0.40
    偉
    0.39
    POSITIVE LOGITS
     selectively
    0.50
     preferentially
    0.47
     supersymmetric
    0.45
     diet
    0.44
     fermionic
    0.43
     commute
    0.43
     câ
    0.43
    ર્ટ
    0.43
     commutes
    0.43
    diet
    0.42
    Activations Density 0.001%

    No Known Activations