© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14636
    Prev
    Next
    INDEX
    Explanations

    hematological terms and blood disorders

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

    terms related to blood cells and hematological conditions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires strongly on terms naming blood components, blood‐cell related measurements, or hematological disorders.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     стене
    -1.39
    b
    -1.27
     Impressive
    -1.23
     décisions
    -1.22
    But
    -1.20
     крепления
    -1.20
     attentes
    -1.18
    者を
    -1.18
    alucía
    -1.16
     kennen
    -1.16
    POSITIVE LOGITS
    щает
    1.48
     not
    1.39
    خي
    1.38
    čů
    1.26
    🩸
    1.23
    ungkapkan
    1.23
     spesielt
    1.23
     pastillas
    1.20
    については
    1.20
    』、
    1.20
    Activations Density 0.196%

    No Known Activations