© 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. 43764
    Prev
    Next
    INDEX
    Explanations

    verbs ending in ing or ed

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

    The neuron strongly activates on the initial letter sequences (roughly four‐ to six‐letter prefixes) of longer, multi‐syllable words (i.e. the word “stems” at their beginnings).

    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
     such
    -2.22
    sometimes
    -1.84
     этими
    -1.77
     unlike
    -1.73
    お待ちしております
    -1.70
    ご了承ください
    -1.66
     pronti
    -1.66
     такую
    -1.64
    鲞
    -1.61
    often
    -1.60
    POSITIVE LOGITS
    gambarkan
    1.60
    fondos
    1.57
     ejecución
    1.53
     Verbreitung
    1.52
    cześ
    1.51
     erity
    1.48
     издание
    1.47
    ява
    1.46
     französischen
    1.44
    䉴
    1.42
    Activations Density 0.174%

    No Known Activations