© 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. 123602
    Prev
    Next
    INDEX
    Explanations

    KPIs and analytics

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

    both informative and entertaining

    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
     rapidity
    0.45
     Airplane
    0.43
     Tidal
    0.42
    섭
    0.42
     Toh
    0.42
     infestations
    0.42
     తీసుకోవ
    0.41
     Thoreau
    0.41
     tidal
    0.41
     isop
    0.40
    POSITIVE LOGITS
    discharge
    0.51
    g
    0.49
     출시
    0.49
    programming
    0.48
    jogo
    0.48
    할
    0.47
    bosch
    0.47
    াহিনীর
    0.47
     अहिले
    0.47
    াল
    0.47
    Activations Density 0.001%

    No Known Activations