© 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. 22-GEMMASCOPE-RES-131K
    7. 69081
    Prev
    Next
    INDEX
    Explanations

    the past tense

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

    This neuron selectively responds to capitalized tokens, i.e. proper names and other words that begin with an uppercase letter.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     sekarang
    -0.93
    zką
    -0.92
     now
    -0.90
    gridColumn
    -0.89
    hörigen
    -0.89
     речо
    -0.87
     normals
    -0.84
    хара
    -0.81
     berbagai
    -0.80
    showing
    -0.79
    POSITIVE LOGITS
    当时
    1.56
    正在
    1.56
     đang
    1.55
     was
    1.51
     sedang
    1.48
     moments
    1.48
    當時
    1.41
     estava
    1.30
     estaba
    1.24
     seconds
    1.23
    Activations Density 0.093%

    No Known Activations