© 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. 39644
    Prev
    Next
    INDEX
    Explanations

    how to / steps

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

    This neuron spotlights call-to-action or “see more” link cues—phrases that introduce or point to additional content (e.g. “Check out this…,” “See how…,” “Read More,” “Related:”).

    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
     it
    -1.33
    kette
    -1.32
     this
    -1.19
     tomto
    -1.13
     promosi
    -1.04
    たびに
    -1.04
     consultato
    -1.02
     войск
    -1.02
     illustratie
    -1.02
    dokument
    -1.02
    POSITIVE LOGITS
     how
    1.77
     ways
    1.19
    '
    1.14
     How
    1.09
    how
    1.03
     -
    1.01
     to
    0.96
    )
    0.96
     faço
    0.96
    風味
    0.94
    Activations Density 0.000%

    No Known Activations