© 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. 129091
    Prev
    Next
    INDEX
    Explanations

    data | database | query

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

    The neuron activates on words meaning “data” (e.g. Portuguese “dados,” Russian “данных,” English “data,” etc.), effectively spotting mentions of data or database contents.

    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
    m
    -3.00
    </h1>
    -3.00
    t
    -2.77
     The
    -2.75
     "
    -2.75
    p
    -2.61
    *
    -2.41
    on
    -2.39
     You
    -2.38
    ka
    -2.33
    POSITIVE LOGITS
     OGSÅ
    2.84
    鮃
    2.67
     masculina
    2.52
     ★★★
    2.45
    utterstock
    2.45
     ⚫
    2.44
     中式
    2.44
    UAGES
    2.36
     ©️
    2.36
    </em>
    2.28
    Activations Density 0.001%

    No Known Activations