© 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. 131744
    Prev
    Next
    INDEX
    Explanations

    return refused, customs form, green collar

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

    convert formats, communication

    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
    rchen
    0.47
    নকে
    0.46
    eket
    0.46
    DBOutput
    0.45
    랐
    0.45
     Paren
    0.44
     Obwohl
    0.44
    取得了
    0.43
    adena
    0.43
    ̀ng
    0.43
    POSITIVE LOGITS
    諜
    0.53
    ਣੀ
    0.52
    числения
    0.51
    ᱭ
    0.50
    ้ำ
    0.50
    computing
    0.49
    ྞ
    0.49
    числи
    0.48
     подачи
    0.48
     সমাজ
    0.47
    Activations Density 0.000%

    No Known Activations