© 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. 34-GEMMASCOPE-RES-131K
    7. 64647
    Prev
    Next
    INDEX
    Explanations

    publishing official notices

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

    The neuron is keyed to the formal headings and announcement phrases (e.g. “Notice,” “Published,” section titles) that appear in government or legal public-notice documents.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    logous
    -0.81
     peppermint
    -0.80
    bakan
    -0.74
    ᵍ
    -0.73
    revet
    -0.72
    hias
    -0.70
    artem
    -0.70
     الوضع
    -0.69
     remind
    -0.69
     Edison
    -0.69
    POSITIVE LOGITS
     notice
    2.44
     publication
    2.05
     notices
    2.03
     Notice
    1.96
     notification
    1.92
    Notice
    1.89
    notice
    1.83
    NOTICE
    1.78
     publishing
    1.78
     newspaper
    1.78
    Activations Density 0.029%

    No Known Activations