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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 20699
    Prev
    Next
    INDEX
    Explanations

    eye, vision, ophthalmology

    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_16_width_262k_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
     вой
    0.53
    َ
    0.52
    LNG
    0.50
    ِ
    0.50
    monitoring
    0.49
     اعتق
    0.48
    ْ
    0.48
    呚
    0.47
     monitoring
    0.47
    )،
    0.46
    POSITIVE LOGITS
     Ophthalmology
    1.06
     glaucoma
    1.04
     ophthal
    0.99
     Retina
    0.99
     optomet
    0.99
     cornea
    0.98
     ophthalm
    0.98
     Ophthalm
    0.95
     Eye
    0.94
     retina
    0.91
    Activations Density 0.071%

    No Known Activations