© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99530
    Prev
    Next
    INDEX
    Explanations

    daily + publication names

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

    The neuron is tuned to spot the word “Daily” when it appears as part of newspaper, magazine, or media outlet names.

    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
    ’
    -3.05
     ,
    -1.89
     มี
    -1.87
     -
    -1.84
     Powerful
    -1.81
     ก็
    -1.81
    </h3>
    -1.78
     avec
    -1.77
     secluded
    -1.76
     Others
    -1.73
    POSITIVE LOGITS
    栳
    2.31
    From
    2.11
     каждый
    2.03
     сс
    1.98
    葙
    1.94
    時に
    1.93
    🢐
    1.92
    珖
    1.83
    謬
    1.81
     łóż
    1.80
    Activations Density 0.017%

    No Known Activations