© 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. 102848
    Prev
    Next
    INDEX
    Explanations

    would like

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

    The neuron fires on past‐tense (or past‐participle) verb forms (e.g. “bile,” “voljela,” “geschrieben”).

    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
    蟶
    -2.44
     benzin
    -2.28
    鼍
    -2.16
    ⎔
    -2.16
    滏
    -2.11
     剧照
    -2.06
    婠
    -2.05
     rése
    -2.05
     maquilla
    -2.00
     africana
    -1.99
    POSITIVE LOGITS
    {
    2.33
    ↵↵
    2.08
    3
    1.95
    would
    1.94
    to
    1.94
    …
    1.91
     would
    1.89
    on
    1.88
     will
    1.87
            
    1.84
    Activations Density 0.019%

    No Known Activations