© 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. 22-GEMMASCOPE-RES-131K
    7. 65491
    Prev
    Next
    INDEX
    Explanations

    articles or posts

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

    The neuron strongly activates on editorial calls for contributions or submissions (e.g., invitations to submit articles).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     ovale
    -0.85
     personalizados
    -0.83
     spelt
    -0.82
    яг
    -0.82
    tabol
    -0.81
    payers
    -0.81
    maki
    -0.80
     상세
    -0.80
    ᄇ
    -0.79
    ᅮ
    -0.78
    POSITIVE LOGITS
     requested
    1.37
     requests
    1.26
     request
    1.17
     slots
    1.09
     Request
    1.04
     selection
    1.04
    requested
    1.03
     contacted
    1.01
     rejected
    0.99
     criteria
    0.97
    Activations Density 0.088%

    No Known Activations