© 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. 70734
    Prev
    Next
    INDEX
    Explanations

    Q: followed by colon

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

    The neuron activates on past-tense verbs ending in “-ed.”

    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
     when
    -1.93
     these
    -1.63
     this
    -1.63
     for
    -1.58
     what
    -1.58
     When
    -1.44
     made
    -1.43
     where
    -1.42
     make
    -1.41
     because
    -1.40
    POSITIVE LOGITS
     strikingly
    1.30
     kulak
    1.27
     inan
    1.23
     participer
    1.23
     malgré
    1.21
    毟
    1.20
     delightfully
    1.19
     revamped
    1.18
     laz
    1.18
     YE
    1.18
    Activations Density 0.000%

    No Known Activations