© 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. 236807
    Prev
    Next
    INDEX
    Explanations

    purchased or leased

    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
    Not in Any Lists

    No Comments

    Negative Logits
    并将
    0.46
    橫
    0.46
     యా
    0.45
    центри
    0.45
    不斷
    0.44
    прият
    0.44
     الرحيم
    0.42
    かって
    0.41
    َف
    0.41
     radius
    0.41
    POSITIVE LOGITS
    ৭
    0.60
     nuovo
    0.47
     nowego
    0.47
    inerja
    0.46
    ombi
    0.46
    hny
    0.45
     wyniki
    0.45
    ální
    0.44
     nieuwe
    0.44
     அகற்ற
    0.44
    Activations Density 0.001%

    No Known Activations