© 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. 10-GEMMASCOPE-RES-131K
    4. 104304
    Prev
    Next
    INDEX
    Explanations

    gone or going

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

    This neuron flags various forms of the verb “go,” such as go, goes, and gone.

    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
     that
    -1.76
     作る
    -1.41
     heath
    -1.38
     of
    -1.31
    😞
    -1.27
    😕
    -1.27
     gdyby
    -1.27
    8
    -1.26
     поэтому
    -1.23
     използва
    -1.22
    POSITIVE LOGITS
    ماعة
    1.44
    iuo
    1.34
     pertama
    1.34
    salms
    1.32
     a
    1.31
    apatalk
    1.31
     sogenannte
    1.30
    mA
    1.26
    ですかね
    1.24
    鞦
    1.23
    Activations Density 0.066%

    No Known Activations