© 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. 36124
    Prev
    Next
    INDEX
    Explanations

    look at or check something

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

    The neuron strongly activates on imperative, call-to-action phrases (e.g. “Take a look,” “Check out,” “Watch”) that urge the reader to view or engage with content.

    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
     These
    -1.27
     like
    -1.19
     Similar
    -1.16
     Many
    -1.12
     This
    -1.10
     Actually
    -1.09
     Along
    -1.08
     ibunya
    -1.07
     similar
    -1.06
    モダン
    -1.05
    POSITIVE LOGITS
     below
    1.43
     conferir
    1.29
     pengar
    1.29
     thuy
    1.26
     nimmer
    1.23
    Takk
    1.22
    วันที่
    1.21
     halte
    1.20
     指輪
    1.18
     vermi
    1.16
    Activations Density 0.016%

    No Known Activations