© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 39589
    Prev
    Next
    INDEX
    Explanations

    soliciting requests and calls

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     when
    -1.02
     quando
    -1.01
     duong
    -0.97
     dopo
    -0.96
     cuando
    -0.95
     tamaños
    -0.91
     khong
    -0.90
    IRMED
    -0.88
     tuong
    -0.88
     победы
    -0.87
    POSITIVE LOGITS
     to
    1.24
     soliciting
    1.23
     for
    1.22
     beckon
    1.21
     inviting
    1.13
     invitation
    1.13
     enticing
    1.09
     terbuka
    1.07
     anyone
    1.05
     anybody
    1.04
    Activations Density 0.068%

    No Known Activations