© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44882
    Prev
    Next
    INDEX
    Explanations

    time to act

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

    The neuron responds to verbs that denote carrying out tasks or procedural actions (e.g., consider, negotiate, file, get through, work on).

    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
     end
    -1.34
    食べ物
    -1.34
    』(
    -1.33
    utschen
    -1.27
    つづく
    -1.27
    　『
    -1.27
    了解更多
    -1.23
    ＞＞
    -1.22
     by
    -1.21
     Ihrem
    -1.20
    POSITIVE LOGITS
    的他
    1.18
     nélkül
    1.12
     zowel
    1.11
    ٧
    1.08
     nabíd
    1.08
     one
    1.07
     bijvoorbeeld
    1.06
     fournies
    1.05
     Frankrijk
    1.05
     forklift
    1.05
    Activations Density 0.030%

    No Known Activations