© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 39453
    Prev
    Next
    INDEX
    Explanations

    just finished or returned

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

    The neuron fires on past‐tense verbs signaling that the writer has just completed or returned from some activity.

    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
     parecen
    -1.46
    {
    -1.35
     cuando
    -1.32
    没有
    -1.32
    魮
    -1.30
    あんな
    -1.29
     puis
    -1.28
     snart
    -1.26
     ponen
    -1.23
     WHEN
    -1.21
    POSITIVE LOGITS
     from
    1.59
     risking
    1.48
     manifests
    1.48
    洐
    1.43
     conforms
    1.36
     洗濯
    1.34
    mails
    1.33
    CONCLUS
    1.33
    出了一
    1.33
     pertains
    1.32
    Activations Density 0.015%

    No Known Activations