© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15378
    Prev
    Next
    INDEX
    Explanations

    hemoglobin (Hb) variants

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

    The neuron activates for "Hb" (hemoglobin) abbreviations in medical and scientific texts.

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

    The neuron detects mentions of hemoglobin variants denoted by “Hb” (often followed by numbers or letters).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ꯷
    -2.94
    駡
    -2.69
    
    -2.56
    HEAST
    -2.53
    
    -2.44
    ༩
    -2.44
     reconoc
    -2.42
    勍
    -2.42
    vať
    -2.41
    ίζει
    -2.41
    POSITIVE LOGITS
    In
    3.16
    in
    3.13
    O
    3.09
    櫚
    2.73
    1
    2.70
    ly
    2.61
     '
    2.53
    o
    2.48
    9
    2.48
     de
    2.45
    Activations Density 0.020%

    No Known Activations