© 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. 71714
    Prev
    Next
    INDEX
    Explanations

    aneurysm

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

    medical terms related to aneurysms and blood vessel conditions.

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

    The neuron strongly activates on subword tokens of “aneurysm” or “aneurysmal,” so it is detecting mentions of aneurysms.

    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
    ).
    -2.89
    ⢌
    -2.61
     aqueles
    -2.55
    ,\\
    -2.53
    那个人
    -2.45
    癰
    -2.45
     regiões
    -2.39
     immense
    -2.34
     determinados
    -2.33
    TypeID
    -2.31
    POSITIVE LOGITS
    禤
    3.38
    T
    3.02
    M
    2.97
    F
    2.94
    B
    2.91
    P
    2.88
    H
    2.86
    E
    2.86
    衕
    2.80
    U
    2.69
    Activations Density 0.018%

    No Known Activations