© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98971
    Prev
    Next
    INDEX
    Explanations

    ASAP, NOW, immediately

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

    The neuron fires on action-oriented calls to the reader—imperatives and promotional verbs urging you to “pick one up,” “check it out,” “get it in your hands,” “needs to end,” 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_34/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
     初
    -0.89
    initial
    -0.89
    always
    -0.88
    猛然
    -0.87
     comunica
    -0.86
     Erkrankungen
    -0.84
     latina
    -0.82
    पि
    -0.81
    лами
    -0.81
     supera
    -0.80
    POSITIVE LOGITS
     ASAP
    5.34
     asap
    5.03
     NOW
    3.25
     pronto
    2.77
     immediately
    2.75
     segera
    2.42
    NOW
    2.39
     sooner
    2.34
     STAT
    2.17
     stat
    2.13
    Activations Density 0.097%

    No Known Activations