© 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. 22-GEMMASCOPE-RES-131K
    7. 33926
    Prev
    Next
    INDEX
    Explanations

    now or still

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

    The neuron detects mentions of limited availability or remaining slots (e.g. “spaces left,” “only … spaces still available,” “register today”).

    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
    Когда
    -1.20
     when
    -1.16
    每年
    -1.14
    eventually
    -1.09
     Quando
    -1.09
     eventually
    -1.09
    詼
    -1.05
    ませんでした
    -1.04
    cuando
    -1.03
    Kiedy
    -1.03
    POSITIVE LOGITS
     still
    1.70
     stále
    1.56
     сейчас
    1.53
     now
    1.52
    引き続き
    1.45
     đang
    1.43
     зараз
    1.41
     jetzt
    1.39
     指輪
    1.38
     already
    1.36
    Activations Density 0.069%

    No Known Activations