© 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. 73181
    Prev
    Next
    INDEX
    Explanations

    welcoming statements

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

    The neuron fires on occurrences of the verb “welcome” (and its inflected forms “welcomed,” “welcomes,” etc.).

    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
    '
    -1.89
    糨
    -1.87
    eclamp
    -1.73
    ﺶ
    -1.68
     You
    -1.66
     Might
    -1.63
    entikan
    -1.59
     on
    -1.58
     When
    -1.57
     fascinating
    -1.53
    POSITIVE LOGITS
    蚡
    2.09
    ቍ
    2.02
    ープン
    1.75
    𞤢
    1.73
    铙
    1.70
     Möglichkeit
    1.70
    abl
    1.69
    躂
    1.67
    ༷
    1.63
    icts
    1.61
    Activations Density 0.009%

    No Known Activations