© 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. 13107
    Prev
    Next
    INDEX
    Explanations

    arterioles

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

    the word fragment "les" in various contexts, particularly in medical and anatomical terms.

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

    This neuron strongly activates on the subword “les” (the exact token “les”), as it appears in various words or names.

    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
    肏
    -2.80
    贽
    -2.70
    衪
    -2.63
    ఞ
    -2.61
    屄
    -2.59
    ︕
    -2.56
    襌
    -2.53
    笮
    -2.52
    欉
    -2.48
    揼
    -2.48
    POSITIVE LOGITS
    les
    3.44
    )
    2.83
    当然
    2.75
    ’
    2.72
    LES
    2.52
    able
    2.48
     '
    2.45
     You
    2.38
     Produkten
    2.34
     When
    2.31
    Activations Density 0.008%

    No Known Activations