© 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. 34-GEMMASCOPE-RES-131K
    7. 58602
    Prev
    Next
    INDEX
    Explanations

    a company or division

    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
     assist
    -0.81
     ļoti
    -0.81
    /−
    -0.81
     any
    -0.79
    etiqueta
    -0.77
    四月
    -0.76
    ांकि
    -0.76
     as
    -0.75
     anything
    -0.75
     zespół
    -0.75
    POSITIVE LOGITS
     division
    1.57
     subsidiary
    1.54
    division
    1.52
     onderdeel
    1.40
     part
    1.38
     divisions
    1.34
     affiliate
    1.32
     component
    1.22
    Division
    1.18
     subsidiaries
    1.18
    Activations Density 0.089%

    No Known Activations