© 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. 10918
    Prev
    Next
    INDEX
    Explanations

    alternative payment or contact methods

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

    This neuron fires on user-directed service instructions or calls to action—phrases telling the reader how to order, contact, or otherwise proceed.

    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
    :
    -1.28
     what
    -1.11
    ᄀ
    -1.05
    ViewImports
    -0.98
    既然
    -0.98
     that
    -0.96
    =
    -0.95
     mostrando
    -0.94
    uable
    -0.94
     contextLoads
    -0.94
    POSITIVE LOGITS
     via
    1.54
     or
    1.34
     through
    1.21
     melalui
    1.20
    Option
    1.17
     hagy
    1.17
     if
    1.16
     by
    1.16
     telephone
    1.15
    巅
    1.14
    Activations Density 0.026%

    No Known Activations