© 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. 66366
    Prev
    Next
    INDEX
    Explanations

    recurring customers and relationships

    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
    enciais
    -1.07
     weiteren
    -0.97
     direzione
    -0.96
     in
    -0.93
     about
    -0.90
     proposito
    -0.90
     further
    -0.90
     but
    -0.90
     derived
    -0.90
    styrelsen
    -0.89
    POSITIVE LOGITS
     regulars
    1.62
     mêmes
    1.27
     loyal
    1.19
     постоян
    1.16
     loy
    1.15
    gypti
    1.09
    בוע
    1.09
     akrab
    1.09
    彼らは
    1.09
     loyalty
    1.08
    Activations Density 0.028%

    No Known Activations