© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 73380
    Prev
    Next
    INDEX
    Explanations

    breaking news

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

    The neuron consistently activates on high‐frequency English function words (common stop words such as “the,” “to,” “when,” “we,” “have,” 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_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
     মা
    -0.75
     ivelany
    -0.75
    ಂಗ
    -0.73
    ḗ
    -0.72
    ittle
    -0.70
     Vene
    -0.69
    饋
    -0.68
     Shrink
    -0.68
    ouden
    -0.68
    inti
    -0.67
    POSITIVE LOGITS
     breaking
    5.84
    breaking
    5.00
    Breaking
    4.88
     Breaking
    4.78
     BREAKING
    4.25
    BREAKING
    4.19
     broke
    2.84
     breaks
    2.69
     break
    2.64
     breaker
    2.56
    Activations Density 0.091%

    No Known Activations