© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 22641
    Prev
    Next
    INDEX
    Explanations

    blood cell and platelet counts

    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
     Architectural
    0.44
    🪵
    0.43
    憬
    0.43
    视频
    0.42
    梦
    0.42
    建筑
    0.41
    逋
    0.41
     부동산
    0.41
    颖
    0.41
    榫
    0.41
    POSITIVE LOGITS
     hemat
    1.98
    Hemat
    1.84
     blood
    1.82
     haemat
    1.81
     thrombocyt
    1.77
     anemia
    1.75
     hematopoietic
    1.75
     Hemat
    1.74
     hemoglobin
    1.73
     platelets
    1.70
    Activations Density 0.028%

    No Known Activations