© 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. 69145
    Prev
    Next
    INDEX
    Explanations

    Publishing entities and proper nouns

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

    The neuron fires on tokens that are part of named organizations or corporate/publisher entity 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
    ꯸
    -3.00
    шают
    -2.39
    笮
    -2.38
     continúas
    -2.36
    柺
    -2.34
    钲
    -2.34
    しました
    -2.34
    푁
    -2.31
     biodivers
    -2.27
    ꦼ
    -2.27
    POSITIVE LOGITS
    .
    3.36
    5
    3.00
    ви
    2.52
    –
    2.50
    -
    2.48
    9
    2.45
    ”
    2.44
    ية
    2.33
    0
    2.31
    ,
    2.28
    Activations Density 0.000%

    No Known Activations