© 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. 82400
    Prev
    Next
    INDEX
    Explanations

    names starting with St

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

    The neuron fires on year-style numbers (four-digit dates) in the text.

    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
     quoque
    -0.71
    ضا
    -0.66
     ngươi
    -0.66
     Missoula
    -0.66
     Mette
    -0.64
     spagnolo
    -0.64
    eser
    -0.64
    LogLevel
    -0.63
    :`
    -0.63
     colpa
    -0.63
    POSITIVE LOGITS
     ST
    3.13
     st
    2.69
    ST
    2.38
     स्ट
    2.28
     STC
    2.22
     St
    2.17
    st
    2.13
     STP
    2.11
    St
    2.00
    スト
    1.98
    Activations Density 0.062%

    No Known Activations