© 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. 22-GEMMASCOPE-RES-131K
    7. 71259
    Prev
    Next
    INDEX
    Explanations

    will have happened

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

    The neuron is sensitive to auxiliary (helping) verbs—forms of “be,” “have,” modals (“will,” “should”), and similar tense-marking verbs.

    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
     of
    -0.96
    0
    -0.91
    包括
    -0.91
     incluye
    -0.88
     certain
    -0.86
    now
    -0.86
     various
    -0.85
    indicates
    -0.85
     এবং
    -0.84
     включает
    -0.81
    POSITIVE LOGITS
     octobre
    1.13
     starts
    1.09
     соу
    1.08
    发表于
    1.08
     शुर
    1.08
    τερ
    1.05
    发布于
    1.02
     dentista
    1.02
    เริ่ม
    1.01
     bonté
    1.01
    Activations Density 0.125%

    No Known Activations