© 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. 99860
    Prev
    Next
    INDEX
    Explanations

    boundary condition(s)

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

    This neuron detects references to boundary conditions (e.g. “boundary,” “conditions,” “boundary condition”) in technical mathematical or PDE contexts.

    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
     There
    -1.66
     bestehende
    -1.55
     combatir
    -1.53
    <bos>
    -1.51
    When
    -1.48
     only
    -1.47
    there
    -1.46
    Creating
    -1.45
     если
    -1.45
     how
    -1.42
    POSITIVE LOGITS
     THOSE
    1.87
     también
    1.74
     alſo
    1.55
    粢
    1.51
    箇所
    1.44
     Fünf
    1.43
    ᎒
    1.40
    こともあります
    1.38
    materia
    1.36
     mierda
    1.36
    Activations Density 0.017%

    No Known Activations