© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 127461
    Prev
    Next
    INDEX
    Explanations

    before followed by action

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

    The neuron fires on verbs (especially present‐participles and key action words) that describe events or actions 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_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
     when
    -1.91
     but
    -1.70
     only
    -1.67
     then
    -1.53
     acercarse
    -1.44
     both
    -1.43
     not
    -1.38
     many
    -1.34
     тогда
    -1.34
     than
    -1.33
    POSITIVE LOGITS
    蠵
    1.38
     syk
    1.31
     viande
    1.31
     outros
    1.30
     rendement
    1.23
    läs
    1.20
    tettu
    1.20
     patrie
    1.18
     situe
    1.17
    鋨
    1.17
    Activations Density 0.043%

    No Known Activations