© 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. 73361
    Prev
    Next
    INDEX
    Explanations

    nep, neptune, nepal, neptunium, neprilysin

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

    The neuron responds to any token containing the letter sequence “Nep.”

    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
    蠵
    -2.63
    0
    -2.50
    呖
    -2.47
    责编
    -2.38
     längere
    -2.23
    Евгений
    -2.23
    疡
    -2.22
     metaphors
    -2.20
    </strong>
    -2.20
    -
    -2.17
    POSITIVE LOGITS
    "
    2.64
     ‘’
    2.64
    </td>
    2.56
    ’?
    2.52
    ’)
    2.42
    aphne
    2.23
     obtiene
    2.23
     consigue
    2.20
    !?!
    2.17
    馓
    2.17
    Activations Density 0.008%

    No Known Activations