© 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. 132758
    Prev
    Next
    INDEX
    Explanations

    gettingquickly

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

    medical knowledge and terms

    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
    主办
    0.43
     ખા
    0.41
     stari
    0.40
    农村
    0.40
    ◞
    0.40
    剧
    0.40
    শক্ত
    0.39
    际
    0.39
    가
    0.39
     mischiev
    0.38
    POSITIVE LOGITS
    b
    0.48
     Wien
    0.48
     literals
    0.47
     A
    0.47
    𝑇
    0.46
    aS
    0.45
     Til
    0.44
     Ratio
    0.44
     Lim
    0.43
    photo
    0.43
    Activations Density 0.000%

    No Known Activations