© 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. 34-GEMMASCOPE-RES-131K
    7. 57615
    Prev
    Next
    INDEX
    Explanations

    membrane properties and functions

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

    This neuron detects the word "membrane" and related concepts in scientific/biological contexts.

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

    The neuron specifically detects mentions of the term “membrane” (including compound forms) in biomedical 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_34/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
     nakalista
    -0.89
    しま
    -0.86
    centages
    -0.81
     zmniejs
    -0.79
     cualquier
    -0.75
     δη
    -0.75
     Совет
    -0.75
    crania
    -0.74
    ဇ
    -0.74
     nervous
    -0.73
    POSITIVE LOGITS
    ous
    1.08
     impermeable
    0.89
    acea
    0.88
     diph
    0.83
     Coins
    0.82
     rupture
    0.81
     permeable
    0.76
    newList
    0.75
    Eduardo
    0.75
     Fram
    0.75
    Activations Density 0.052%

    No Known Activations