© 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. 40-GEMMASCOPE-2-RES-262K
    7. 20815
    Prev
    Next
    INDEX
    Explanations

    medical conditions and findings

    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_40_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
     پیسې
    0.61
    🚀
    0.55
    㓶
    0.55
     території
    0.53
    㗽
    0.53
    ธุรกิจ
    0.52
    眹
    0.52
     підприєм
    0.51
     买
    0.51
     Nuggets
    0.50
    POSITIVE LOGITS
     lesions
    0.99
     abnormalities
    0.91
     abscess
    0.86
     idiopathic
    0.86
     ischemic
    0.85
     ischemia
    0.85
     urinary
    0.84
     necrosis
    0.81
     esophageal
    0.81
     inflammatory
    0.81
    Activations Density 0.052%

    No Known Activations