© 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. 99351
    Prev
    Next
    INDEX
    Explanations

    aspects of

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

    This neuron strongly detects the preposition “of,” especially when it appears in the phrase “aspects of.”

    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
     depiction
    -2.20
    '}
    -1.89
    宬
    -1.83
     bande
    -1.78
    ituaries
    -1.77
    再一次
    -1.77
     It
    -1.75
    ᥬ
    -1.73
    穿上
    -1.70
    虜
    -1.69
    POSITIVE LOGITS
     that
    2.06
     burgeoning
    1.91
     this
    1.88
     their
    1.85
    袿
    1.82
     these
    1.80
    AutoresizingMask
    1.78
     our
    1.76
     enemmän
    1.71
    t
    1.68
    Activations Density 0.023%

    No Known Activations