© 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. 31-GEMMASCOPE-2-RES-65K
    7. 31704
    Prev
    Next
    INDEX
    Explanations

    parsing numbers in code

    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_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Р
    0.61
    Д
    0.52
    Й
    0.51
    Гор
    0.50
    В
    0.49
    До
    0.48
    Ло
    0.48
    Доб
    0.48
    зг
    0.47
    У
    0.47
    POSITIVE LOGITS
     enhance
    0.52
     offers
    0.52
     deres
    0.50
     awarded
    0.49
     avatars
    0.48
     parcela
    0.48
     enhances
    0.47
     populate
    0.47
     melee
    0.47
     entrees
    0.47
    Activations Density 0.009%

    No Known Activations