© 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. 72586
    Prev
    Next
    INDEX
    Explanations

    boundary behaviour and conditions

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

    This neuron detects occurrences of the term “boundary” (especially in phrases like “boundary condition” or “boundary behaviour”) in mathematical text.

    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
    )
    -2.55
    We
    -2.13
     Your
    -2.00
    indelijk
    -1.96
    gezogen
    -1.94
    which
    -1.92
    or
    -1.89
     planen
    -1.88
     europe
    -1.87
     —
    -1.85
    POSITIVE LOGITS
    䉴
    2.80
     sincere
    2.75
    洐
    2.70
     weary
    2.50
     カフェ
    2.44
    翆
    2.42
    牁
    2.41
    最后由
    2.36
    ra
    2.34
    おわりに
    2.28
    Activations Density 0.004%

    No Known Activations