© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 18415
    Prev
    Next
    INDEX
    Explanations

    key-value assignments

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

    code assignments and definitions

    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
    珍惜
    0.43
     نکن
    0.43
    侎
    0.42
    <start_of_turn>
    0.41
    <unused32>
    0.41
    ద్దా
    0.40
    ("|"+"
    0.40
    ご注意
    0.40
    淢
    0.40
    Leave
    0.40
    POSITIVE LOGITS
     is
    0.62
    :",
    0.57
    :$
    0.57
    :";
    0.56
    :
    0.56
    :");
    0.54
     =
    0.52
    :")
    0.51
     :
    0.50
     equals
    0.50
    Activations Density 0.000%

    No Known Activations