© 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. 185875
    Prev
    Next
    INDEX
    Explanations

    antibiotic treatments

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

    instructions and content

    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
     Guided
    0.47
    Guided
    0.47
    Computation
    0.46
    Faces
    0.43
    Focused
    0.43
     Demonstr
    0.42
    Accessibility
    0.41
    仴
    0.41
     Фі
    0.41
     Funded
    0.41
    POSITIVE LOGITS
     diphenyl
    0.54
     catheters
    0.46
     shingles
    0.45
     allergic
    0.44
     chemically
    0.44
     corticosteroids
    0.44
     nitric
    0.44
     crud
    0.44
    utica
    0.44
     anuv
    0.43
    Activations Density 0.002%

    No Known Activations