© 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. 176300
    Prev
    Next
    INDEX
    Explanations

    fulfillment and lowering

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

    selection or choice

    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
    estimators
    0.50
    leads
    0.48
    亍
    0.47
    water
    0.45
    wright
    0.45
    oplast
    0.43
    leading
    0.43
    barn
    0.43
    apsible
    0.43
    catcher
    0.43
    POSITIVE LOGITS
    รียม
    0.56
    াত
    0.54
     khởi
    0.51
     choix
    0.50
     cứu
    0.50
     seleção
    0.50
    ן
    0.50
     auswählen
    0.50
     chois
    0.49
     araşt
    0.49
    Activations Density 0.001%

    No Known Activations