© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72201
    Prev
    Next
    INDEX
    Explanations

    proper nouns and places

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

    This neuron activates on proper names and other capitalized named entities.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    licts
    -0.81
    有難
    -0.75
    igten
    -0.75
    Ambos
    -0.74
     فقال
    -0.73
    而非
    -0.71
    但这
    -0.71
     quá
    -0.71
     Coe
    -0.71
     unsolved
    -0.70
    POSITIVE LOGITS
    sog
    0.87
    attempts
    0.84
     objections
    0.84
    šech
    0.84
     attempts
    0.83
     niech
    0.81
     définitivement
    0.81
     malzeme
    0.79
     była
    0.79
    lizes
    0.79
    Activations Density 0.071%

    No Known Activations