© 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. 2592
    Prev
    Next
    INDEX
    Explanations

    breakthrough therapies and accelerated approval

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

    drug regulatory approval

    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
    高志森
    0.71
    怅
    0.65
    勋
    0.62
    伥
    0.59
    鄞
    0.57
    堞
    0.57
    机场
    0.56
    豳
    0.56
    抚
    0.55
    岖
    0.55
    POSITIVE LOGITS
     FDA
    1.23
     pharmaceutical
    1.14
     preclinical
    1.07
     drug
    1.04
    FDA
    1.04
     vaccine
    1.02
     pharmacokinetic
    0.99
     medicamentos
    0.98
     medicines
    0.97
     pharmaceuticals
    0.97
    Activations Density 0.177%

    No Known Activations