© 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. 113858
    Prev
    Next
    INDEX
    Explanations

    common word pairs

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

    conversion to units

    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
     воен
    0.51
     military
    0.46
    <0xB9>
    0.45
     builders
    0.44
     его
    0.43
    ᱘
    0.43
     дер
    0.42
    uild
    0.42
    if
    0.42
    きましたが
    0.42
    POSITIVE LOGITS
     Física
    0.50
     விகி
    0.49
     Aeronaut
    0.48
    အတ
    0.47
    اقات
    0.45
    😥
    0.44
    등급
    0.43
    దిక
    0.43
     aerodynamics
    0.43
     affirme
    0.43
    Activations Density 0.000%

    No Known Activations