© 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. 111837
    Prev
    Next
    INDEX
    Explanations

    biological vesicles

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

    terminology related to lipid vesicles and liposomes in scientific contexts.

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

    The neuron detects mentions of lipid-based vesicular structures—e.g. liposomes, vesicles, micelles.

    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
    ne
    -2.22
    ing
    -1.95
    or
    -1.95
     Gennaio
    -1.95
    first
    -1.91
     épisode
    -1.88
    no
    -1.82
    now
    -1.80
    人
    -1.79
    in
    -1.77
    POSITIVE LOGITS
    <bos>
    1.81
     conectados
    1.78
    哢
    1.71
     kateg
    1.67
    bricas
    1.67
     animados
    1.65
     particularmente
    1.62
     Because
    1.61
    蜮
    1.59
     preparados
    1.59
    Activations Density 0.107%

    No Known Activations