© 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. 54019
    Prev
    Next
    INDEX
    Explanations

    British physicist

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

    COBRA and ethical discussions

    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
    傾向
    0.49
     associating
    0.44
     tutor
    0.43
     rapidity
    0.43
    й
    0.42
    ंश
    0.42
     свободно
    0.42
     є
    0.41
     placing
    0.41
     placé
    0.41
    POSITIVE LOGITS
     представителей
    0.48
    雏
    0.47
     обсу
    0.46
    众人
    0.45
    董事长
    0.45
    宣布
    0.45
     महीनों
    0.45
     представители
    0.44
    提出了
    0.44
    全面的
    0.43
    Activations Density 0.000%

    No Known Activations