© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86353
    Prev
    Next
    INDEX
    Explanations

    considering future actions

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

    The neuron fires on English verbs or verbal nouns in their “-ing” form (present participles/gerunds).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     fyra
    -1.53
     två
    -1.49
     varandra
    -1.44
     malheureux
    -1.40
     œil
    -1.36
     mépris
    -1.35
    刄
    -1.30
     první
    -1.28
     châssis
    -1.26
     nästan
    -1.25
    POSITIVE LOGITS
     as
    1.77
     in
    1.73
     at
    1.73
     but
    1.63
     even
    1.62
     over
    1.45
     just
    1.41
     without
    1.40
     actually
    1.39
    なのですが
    1.35
    Activations Density 0.113%

    No Known Activations