© 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. 105385
    Prev
    Next
    INDEX
    Explanations

    names of newspapers and publications

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

    The neuron consistently fires on occurrences of the word “Tribune” (e.g. newspaper bylines).

    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
    大半
    -2.97
     neuen
    -2.97
     Interested
    -2.95
     unending
    -2.89
     avec
    -2.84
    actéristi
    -2.83
     маленьких
    -2.77
     nowych
    -2.73
    𖣘
    -2.69
     Seriously
    -2.63
    POSITIVE LOGITS
    ⦊
    3.08
    釓
    2.89
    狆
    2.83
    (
    2.80
    ↵↵
    2.69
    💞
    2.66
    💌
    2.44
    猡
    2.38
     THOUGH
    2.38
    ра
    2.38
    Activations Density 0.001%

    No Known Activations