© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129128
    Prev
    Next
    INDEX
    Explanations

    dealers, distributors, partners, agents

    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
     people
    -1.18
     research
    -1.12
     topics
    -1.09
    工厂
    -1.05
     items
    -1.05
     muñecas
    -1.03
     three
    -1.02
     ingredients
    -1.02
     two
    -1.02
     non
    -1.02
    POSITIVE LOGITS
     distribut
    1.20
    袿
    1.11
     Territories
    1.09
    UserAgent
    1.05
     HONOR
    1.05
     DISTRIB
    1.03
     territor
    1.02
    ólogos
    1.02
     koi
    1.02
     opérateurs
    1.02
    Activations Density 0.057%

    No Known Activations