© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 224704
    Prev
    Next
    INDEX
    Explanations

    website addresses and specific entities

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

    languages and translation

    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
     صہیون
    0.54
     শরনার্থ
    0.50
     канторы
    0.49
     적극
    0.49
    庙
    0.49
    RESOLUTION
    0.48
    ávez
    0.48
    ogramDetails
    0.47
     tranquila
    0.46
     ставка
    0.46
    POSITIVE LOGITS
     db
    0.50
    0.49
    db
    0.47
     board
    0.46
    if
    0.46
     ed
    0.46
                                   
    0.45
    do
    0.45
                             
    0.45
    <0x0D>
    0.43
    Activations Density 0.000%

    No Known Activations