© 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. 129007
    Prev
    Next
    INDEX
    Explanations

    first names followed by surnames

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

    The neuron strongly activates on capitalized proper names (e.g. personal names and named entities).

    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
     Когда
    -2.92
     sowohl
    -2.59
     शुर
    -2.58
    瀦
    -2.53
     hauptsächlich
    -2.53
     When
    -2.50
     We
    -2.44
    虓
    -2.41
    棪
    -2.38
    笮
    -2.36
    POSITIVE LOGITS
    A
    4.47
    {
    3.16
    就是
    2.95
    <em>
    2.94
    '
    2.84
    F
    2.78
    其他
    2.69
    D
    2.63
    2
    2.63
     {
    2.63
    Activations Density 0.014%

    No Known Activations