© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13846
    Prev
    Next
    INDEX
    Explanations

    hematologic disease

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

    The neuron selectively activates on technical mentions of hematopoietic (blood) stem cells and their related progenitor populations and differentiation contexts.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    弋
    0.62
     욕
    0.62
    聾
    0.60
     Tort
    0.59
     Pepper
    0.59
     Statue
    0.58
     Southport
    0.58
     Riot
    0.57
     درخت
    0.56
    龜
    0.56
    POSITIVE LOGITS
     hemoglobin
    1.70
     hemat
    1.67
     hematopoietic
    1.63
     hemolysis
    1.60
     Hemat
    1.59
     clotting
    1.56
    Hemat
    1.56
     haemat
    1.53
     thrombocyt
    1.49
     coagulation
    1.44
    Activations Density 0.180%

    No Known Activations