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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 10737
    Prev
    Next
    INDEX
    Explanations

    categories 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-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     кілька
    0.55
     a
    0.54
     ಕಡಿಮೆ
    0.46
    我不
    0.45
     більш
    0.45
     такі
    0.44
    ಾಗಿತ್ತು
    0.44
     మి
    0.43
    хід
    0.43
    ૉ
    0.42
    POSITIVE LOGITS
     உரிமை
    0.53
     fundamento
    0.51
    thood
    0.50
     belong
    0.47
     intrins
    0.47
     deserve
    0.45
    进士
    0.45
     принадлежа
    0.45
     toegang
    0.45
     принадлежит
    0.45
    Activations Density 0.016%

    No Known Activations