© 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. 128337
    Prev
    Next
    INDEX
    Explanations

    free time

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

    The neuron identifies mentions of people’s available or “free” time (especially the collocation “free time”).

    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
     hemel
    -1.33
     perils
    -1.23
    illige
    -1.18
     they
    -1.15
     alimenti
    -1.12
     comunica
    -1.11
     建物
    -1.11
    wać
    -1.10
     tiek
    -1.09
     început
    -1.08
    POSITIVE LOGITS
     солнца
    1.30
    BrowserModule
    1.23
     bahwa
    1.23
     Only
    1.22
    šia
    1.21
    dus
    1.20
     ͡
    1.18
     نشده
    1.17
     Previously
    1.17
     Either
    1.17
    Activations Density 0.020%

    No Known Activations