© 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. 95357
    Prev
    Next
    INDEX
    Explanations

    explaining results or reasons

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

    The neuron is keyed to discourse markers and sequencing/connective words (e.g. “in order,” “second,” “because,” “especially,” “TODO,” etc.).

    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
     .........
    -1.47
     Dinas
    -1.42
     .............
    -1.40
     ,.
    -1.38
     ............
    -1.37
     .......
    -1.36
     ...........
    -1.33
     siè
    -1.33
     berbagai
    -1.32
     både
    -1.30
    POSITIVE LOGITS
     in
    1.55
     if
    1.52
     new
    1.41
    One
    1.36
     innovative
    1.25
    ”
    1.23
     noteworthy
    1.21
     on
    1.20
     не
    1.20
     unusually
    1.19
    Activations Density 0.061%

    No Known Activations