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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13350
    Prev
    Next
    INDEX
    Explanations

    modified, seasoned, or processed

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

    The neuron strongly activates on past-participles (verbs in their “-ed” or “-ated” form) used adjectivally.

    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
    despite
    -1.57
    regardless
    -1.32
     quantités
    -1.27
     WITHIN
    -1.26
     rembour
    -1.26
     malgré
    -1.24
    primarily
    -1.23
     contraintes
    -1.23
     despi
    -1.22
    simult
    -1.21
    POSITIVE LOGITS
     with
    3.16
     by
    2.45
     into
    2.17
     in
    1.88
     from
    1.86
     to
    1.79
     through
    1.69
     as
    1.68
     for
    1.65
     on
    1.59
    Activations Density 0.088%

    No Known Activations