© 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. 73695
    Prev
    Next
    INDEX
    Explanations

    a lot

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

    The neuron strongly activates on first-person action and thought verbs (e.g. “tried,” “searched,” “thinking,” “spent,” “using”)—i.e. verbs describing what the writer did or thought.

    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
    没有任何
    -0.91
    zzá
    -0.86
    ítő
    -0.84
    ارة
    -0.84
    "))
    -0.83
    ौ
    -0.82
    ња
    -0.82
     Slightly
    -0.82
     '',
    -0.81
     Tole
    -0.81
    POSITIVE LOGITS
     alot
    5.69
     lot
    4.81
     lots
    4.75
    Lots
    3.83
     beaucoup
    3.47
    alot
    3.45
    lots
    3.44
     Lots
    3.31
    很多
    3.22
     banyak
    3.06
    Activations Density 0.234%

    No Known Activations