© 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. 34-GEMMASCOPE-RES-131K
    4. 91117
    Prev
    Next
    INDEX
    Explanations

    organization

    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_34/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
    hages
    -0.78
     ?$
    -0.77
     stools
    -0.76
    },$
    -0.71
     okolí
    -0.71
     všetky
    -0.71
    ございました
    -0.71
    转向
    -0.69
     dieťa
    -0.69
    together
    -0.68
    POSITIVE LOGITS
     organization
    2.69
    Organization
    2.34
     organisation
    2.34
    organization
    2.28
     ORGANIZATION
    2.25
     Organization
    2.08
    组织
    2.05
    ORGANIZATION
    1.96
     organización
    1.95
    Organisation
    1.88
    Activations Density 0.031%

    No Known Activations