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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76829
    Prev
    Next
    INDEX
    Explanations

    Hebrew and proper nouns

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

    The neuron fires on the “is” in the canonical “X is a…” definitional opening sentence of Wikipedia‐style entries.

    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
     meningkatkan
    -0.83
    Pcd
    -0.74
    るのが
    -0.74
    を失
    -0.73
    SYMBOL
    -0.73
    Symbol
    -0.73
    しますが
    -0.73
    ingi
    -0.73
     aden
    -0.73
    λλην
    -0.72
    POSITIVE LOGITS
     הז
    1.02
    ➶
    1.01
    ז
    0.98
     ז
    0.95
     Weeknd
    0.85
    PHY
    0.81
    Reminder
    0.80
    nytimes
    0.79
     菲
    0.78
     Reminder
    0.77
    Activations Density 0.016%

    No Known Activations