© 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. 10-GEMMASCOPE-RES-131K
    7. 86485
    Prev
    Next
    INDEX
    Explanations

    hemo- prefix, carboxylic acid

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

    This neuron activates for scientific and medical terminology related to blood and biochemical compounds.

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

    This neuron strongly activates on occurrences of the substring “hemo” (e.g. in words like hemocoel, hemopoietic, hemodialysis, hemostatic).

    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
    1
    -4.41
    7
    -3.58
    2
    -3.50
    5
    -3.39
    3
    -3.39
    6
    -3.30
    4
    -3.28
    8
    -3.22
    0
    -3.14
    9
    -3.13
    POSITIVE LOGITS
    裢
    2.95
    㩒
    2.86
    縂
    2.84
    嘡
    2.83
    粄
    2.78
    Ꮟ
    2.75
    嗵
    2.73
     休閒
    2.70
    clientY
    2.67
    慙
    2.63
    Activations Density 0.090%

    No Known Activations