© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49772
    Prev
    Next
    INDEX
    Explanations

    television presenters and hosts

    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
    nv
    -0.87
    apar
    -0.81
     dodgy
    -0.79
    拡張
    -0.76
    Organiser
    -0.74
     Organisations
    -0.73
    欧美
    -0.72
     customise
    -0.71
    ostringstream
    -0.71
    oxidant
    -0.71
    POSITIVE LOGITS
     presenter
    1.25
     presenters
    1.25
     Strictly
    1.09
     viewers
    1.04
     ITV
    1.02
    presenter
    0.99
     breakfast
    0.99
     Presenter
    0.93
     devrait
    0.88
     Loose
    0.87
    Activations Density 0.009%

    No Known Activations