© 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. 71117
    Prev
    Next
    INDEX
    Explanations

    better late than never

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

    eventful year or impactful experiences

    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
    о
    0.44
    ཥ
    0.41
    viene
    0.39
     своих
    0.39
     използ
    0.39
    зи
    0.38
    ྵ
    0.38
    рес
    0.38
     религиоз
    0.38
    䈤
    0.38
    POSITIVE LOGITS
     underwhelming
    0.51
     epoch
    0.46
    सदी
    0.46
     പങ്കെടു
    0.45
     navigated
    0.45
    失败
    0.44
     participantes
    0.44
     Teilnehmer
    0.44
     impactful
    0.44
     udział
    0.43
    Activations Density 0.004%

    No Known Activations