© 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. 10-GEMMASCOPE-RES-131K
    7. 39863
    Prev
    Next
    INDEX
    Explanations

    odd or occasional item

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

    This neuron lights up on content words that are relatively uncommon or infrequent in the text.

    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
    喾
    -1.95
    liegenden
    -1.91
    ꯶
    -1.86
     anunció
    -1.84
    ཫ
    -1.82
    当我
    -1.77
     鸭
    -1.72
    勦
    -1.70
    空间
    -1.70
    Här
    -1.70
    POSITIVE LOGITS
    StoryboardSegue
    2.48
    which
    2.25
    之以
    2.20
     of
    2.06
    tură
    2.03
     Which
    1.91
     answer
    1.90
    м
    1.90
     one
    1.89
    飚
    1.89
    Activations Density 0.014%

    No Known Activations