© 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. 147530
    Prev
    Next
    INDEX
    Explanations

    after the

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

    qualities of scale, state, or level

    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
     The
    0.30
     government
    0.30
     My
    0.29
     তবে
    0.29
      
    0.29
     cybersecurity
    0.28
    myapp
    0.28
    The
    0.27
     financial
    0.27
    a
    0.27
    POSITIVE LOGITS
     tych
    0.33
    utlich
    0.30
     verwendeten
    0.30
     правой
    0.30
    يل
    0.29
    )}^{\
    0.29
     gouttes
    0.29
    䢌
    0.29
    ouveau
    0.28
     noires
    0.28
    Activations Density 0.038%

    No Known Activations