© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 38410
    Prev
    Next
    INDEX
    Explanations

    will be doing

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

    The neuron strongly fires on future‐tense auxiliaries and related tokens (e.g. “will,” “‘ll,” “be,” “holding”) that signal planned or forthcoming actions.

    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
     probably
    -1.08
     seen
    -0.97
     possibly
    -0.95
     which
    -0.94
     sometimes
    -0.93
     new
    -0.93
     often
    -0.90
     perhaps
    -0.90
     maybe
    -0.89
     viewed
    -0.88
    POSITIVE LOGITS
     hosting
    1.31
     host
    1.22
    Sinopse
    1.14
     AGAIN
    1.13
     hosts
    1.08
     ponownie
    1.01
    Excerpt
    1.01
     مرة
    0.98
    offering
    0.98
    once
    0.97
    Activations Density 0.053%

    No Known Activations