© 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. 7077
    Prev
    Next
    INDEX
    Explanations

    science academies and ministries

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

    institutional affiliations with "Academy of Sciences" or similar academic organizations.

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

    This neuron spots occurrences of institutional affiliation names by detecting tokens like “Sci,” “Sciences,” and similar parts of “Academy of Sciences.”

    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
    ERS
    -2.06
    竦
    -1.78
    但却
    -1.77
    但她
    -1.75
     oscuro
    -1.74
    但不
    -1.73
    复杂的
    -1.71
    !".
    -1.65
    ,/
    -1.64
    特意
    -1.63
    POSITIVE LOGITS
     to
    1.91
    {
    1.90
     for
    1.78
     "")
    1.63
    𝔻
    1.61
    )
    1.60
     are
    1.59
    ਃ
    1.59
    ınız
    1.57
     製造
    1.55
    Activations Density 0.005%

    No Known Activations