© 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. 81603
    Prev
    Next
    INDEX
    Explanations

    what will happen next

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

    The neuron strongly fires on English modal or auxiliary verbs (and related markers of possibility/future), e.g. may, will, could, usually, means.

    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
    här
    -1.24
     sentimos
    -1.20
    Ⴀ
    -1.12
     slike
    -1.09
    filtr
    -1.08
     isto
    -1.07
    nehå
    -1.05
     gré
    -1.05
    醅
    -1.04
     Eventos
    -1.03
    POSITIVE LOGITS
     happen
    1.96
     happening
    1.87
     happened
    1.82
     happens
    1.70
     then
    1.69
     why
    1.39
     all
    1.31
     true
    1.27
     include
    1.27
     includes
    1.24
    Activations Density 0.056%

    No Known Activations