© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118391
    Prev
    Next
    INDEX
    Explanations

    action followed by in

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

    This neuron lights up on general mid-frequency English words (common verbs, adverbs, and pronouns) rather than on specialized or rare terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ására
    -0.77
     contribuer
    -0.77
    AGEMENT
    -0.77
    気になって
    -0.74
     بعد
    -0.74
     течение
    -0.74
    łą
    -0.74
     cung
    -0.73
    dout
    -0.72
    忡
    -0.72
    POSITIVE LOGITS
     in
    3.08
     σε
    1.54
    grouped
    0.89
     occurs
    0.86
     בצ
    0.85
    成
    0.84
     pairwise
    0.84
     dalam
    0.84
    Σε
    0.83
     grouped
    0.82
    Activations Density 0.061%

    No Known Activations