© 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. 22-GEMMASCOPE-RES-131K
    7. 38570
    Prev
    Next
    INDEX
    Explanations

    now introducing new statement or question

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

    The neuron strongly activates on the discourse transition word “now” (and its capitalized “Now”) marking a shift in the speaker’s focus.

    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
     mindig
    -1.37
    believe
    -1.29
     hebben
    -1.26
    Ꮠ
    -1.26
    recently
    -1.21
     côn
    -1.20
     estómago
    -1.20
    襁
    -1.19
    inerario
    -1.19
    dding
    -1.18
    POSITIVE LOGITS
    If
    1.29
    While
    1.27
    From
    1.25
    Unlike
    1.24
    What
    1.21
    !!!
    1.20
    Since
    1.19
    Although
    1.19
    !!!!
    1.17
    !!!!!
    1.17
    Activations Density 0.021%

    No Known Activations