© 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. 13141
    Prev
    Next
    INDEX
    Explanations

    know what is happening

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

    The neuron flags phrases that convey informing or updating someone (e.g. “knew what was happening every step of the way,” “keep you abreast of your case’s progress”).

    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
     chrétienne
    -0.88
     to
    -0.85
    rlrl
    -0.84
     for
    -0.84
    mbh
    -0.80
    Coords
    -0.79
    有些人
    -0.79
    ‌است
    -0.79
    玉ねぎ
    -0.79
    ׇ
    -0.78
    POSITIVE LOGITS
     why
    1.88
     how
    1.38
     what
    1.22
     explain
    1.21
     explaining
    1.12
     proposed
    1.09
    why
    1.07
     explanation
    1.05
     changes
    1.04
     progress
    1.04
    Activations Density 0.028%

    No Known Activations