© 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. 72576
    Prev
    Next
    INDEX
    Explanations

    Welcome to

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

    The neuron spikes strongly on instances of the greeting “Welcome,” especially at the start of a post or section.

    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
    ',
    -1.71
    胳
    -1.66
     której
    -1.64
     każ
    -1.63
    erráneo
    -1.59
    ȹ
    -1.59
     její
    -1.57
    "
    -1.55
     frecuentes
    -1.55
     relevancia
    -1.55
    POSITIVE LOGITS
     我们
    1.90
     to
    1.80
    ’
    1.72
    但这
    1.70
    輊
    1.66
    s
    1.62
     $('.
    1.59
    ,
    1.58
    핥
    1.57
     hikay
    1.56
    Activations Density 0.007%

    No Known Activations