© 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. 130177
    Prev
    Next
    INDEX
    Explanations

    also, in addition

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

    Andhra Pradesh

    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
     dragged
    0.47
     ఒకటి
    0.46
     Ram
    0.46
    öd
    0.45
     ಅಧಿಕಾರಿ
    0.45
     Мари
    0.44
     radiators
    0.44
    氙
    0.43
     リュ
    0.43
     calamities
    0.42
    POSITIVE LOGITS
     també
    0.56
     envers
    0.52
     aussi
    0.52
     также
    0.51
     também
    0.50
     también
    0.48
     cũng
    0.48
     też
    0.47
     Juga
    0.47
     također
    0.47
    Activations Density 0.001%

    No Known Activations