© 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. 58442
    Prev
    Next
    INDEX
    Explanations

    future events and actions

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

    The neuron strongly activates on future‐tense auxiliaries (especially “will,” “be,” and other scheduling verbs) that signal upcoming or scheduled events.

    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
     that
    -2.19
     what
    -2.13
     why
    -1.77
     how
    -1.59
     Для
    -1.48
     now
    -1.45
     where
    -1.45
     Ubicación
    -1.43
     today
    -1.39
     more
    -1.38
    POSITIVE LOGITS
     illustre
    1.53
     appartement
    1.51
     Parlement
    1.43
    𝑒
    1.41
     alho
    1.40
     verbe
    1.40
     populaire
    1.38
     origine
    1.38
     industrie
    1.37
     larmes
    1.37
    Activations Density 0.053%

    No Known Activations