© 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. 34-GEMMASCOPE-RES-131K
    7. 73676
    Prev
    Next
    INDEX
    Explanations

    episode air dates

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

    The neuron fires on numeric tokens (digit sequences) in markup or code.

    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
     μην
    -0.94
    pach
    -0.81
    ♋
    -0.80
    vel
    -0.79
     Emails
    -0.78
    ણ
    -0.75
    矿
    -0.75
     Paragraph
    -0.74
     вѣ
    -0.72
     vel
    -0.71
    POSITIVE LOGITS
     season
    2.36
     episode
    2.16
     seasons
    2.05
     episodes
    1.91
     Season
    1.85
    Season
    1.77
    season
    1.72
    episode
    1.70
     SEASON
    1.62
     Episode
    1.60
    Activations Density 0.019%

    No Known Activations