© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8975
    Prev
    Next
    INDEX
    Explanations

    publisher or publishing

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

    The neuron fires strongly on words and word pieces related to publication credits (e.g. “Publish,” “Published,” “Publisher,” “Publishing,” “by,” 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
    "
    -2.16
     are
    -2.03
    шают
    -1.82
     protože
    -1.80
    躄
    -1.76
    反应过来
    -1.72
    徊
    -1.69
    C
    -1.65
    cellona
    -1.61
    曩
    -1.59
    POSITIVE LOGITS
    ementara
    2.00
    jaqueta
    1.94
    ется
    1.80
    勠
    1.78
     penerima
    1.78
    此时
    1.72
     België
    1.70
    鈇
    1.67
    sukienka
    1.66
     cancelación
    1.64
    Activations Density 0.049%

    No Known Activations