© 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. 10-GEMMASCOPE-RES-131K
    7. 60372
    Prev
    Next
    INDEX
    Explanations

    fraught with

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

    The neuron strongly activates on past‐participle adjectives (–ed forms) used to describe things (e.g. “fraught,” “covered,” “loaded,” “replete,” “lined,” “drenched”).

    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
     což
    -1.52
     Республики
    -1.47
     če
    -1.45
     --;
    -1.45
     last
    -1.41
     what
    -1.41
    ==$
    -1.41
    しないと
    -1.41
    )]=
    -1.40
    鹪
    -1.39
    POSITIVE LOGITS
     imprend
    1.55
    たくさんの
    1.52
     solidified
    1.52
    この日は
    1.50
    ,*
    1.50
    ・・・・・・・・
    1.50
    いろんな
    1.49
     Zweifel
    1.48
    Both
    1.48
     resulted
    1.48
    Activations Density 0.077%

    No Known Activations