© 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. 3042
    Prev
    Next
    INDEX
    Explanations

    owned by media companies

    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
     payers
    -0.77
     Bedürfn
    -0.70
    ordes
    -0.69
     Gall
    -0.69
     ફ
    -0.68
     piping
    -0.68
     iPod
    -0.68
     OVA
    -0.67
     Airbnb
    -0.67
     AirPods
    -0.67
    POSITIVE LOGITS
     Hearst
    1.85
     Scripps
    1.36
     Meredith
    1.19
     McCl
    1.13
    Meredith
    1.11
     Condé
    1.10
     Conde
    1.05
     Cox
    1.05
     Media
    1.01
     Bauer
    0.98
    Activations Density 0.123%

    No Known Activations