© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79189
    Prev
    Next
    INDEX
    Explanations

    Times followed by specific words

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

    The neuron strongly activates on occurrences of the string “times” (in any case or usage).

    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
     time
    -1.63
    ervant
    -0.91
     thời
    -0.90
    愎
    -0.87
     waktu
    -0.83
     сиро
    -0.82
    
    -0.81
     времени
    -0.81
    tbx
    -0.80
     tijd
    -0.80
    POSITIVE LOGITS
    cales
    1.38
    it
    0.99
    tables
    0.98
    times
    0.98
    oms
    0.96
    Times
    0.93
    rs
    0.89
    剮
    0.88
    ls
    0.87
    dz
    0.87
    Activations Density 0.025%

    No Known Activations