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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 4274
    Prev
    Next
    INDEX
    Explanations

    blood cell diagnostics

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

    terminology related to blood cells, particularly erythrocytes and blood components.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    τικό
    -0.78
    дования
    -0.74
    krivelse
    -0.73
     гостей
    -0.73
     Samoa
    -0.71
     grantee
    -0.70
    PushMatrix
    -0.69
     Warriors
    -0.69
    astéro
    -0.69
     GSC
    -0.68
    POSITIVE LOGITS
     мем
    0.79
    dań
    0.78
    lifetime
    0.74
     Kell
    0.72
     lifespan
    0.72
     rendus
    0.71
    Verts
    0.71
     saline
    0.69
    yaw
    0.68
     McDonnell
    0.67
    Activations Density 0.121%

    No Known Activations