© 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. 22-GEMMASCOPE-RES-131K
    7. 14505
    Prev
    Next
    INDEX
    Explanations

    legal advice and status updates

    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
     замок
    -0.86
     viejas
    -0.84
    istán
    -0.84
     harmonie
    -0.81
    cześ
    -0.81
    繭
    -0.81
     Taip
    -0.81
    τικών
    -0.80
     ειδ
    -0.79
    ਆਂ
    -0.78
    POSITIVE LOGITS
     legally
    1.27
     legal
    1.24
    status
    1.20
     protection
    1.13
     status
    1.11
     rights
    1.06
     automatically
    1.05
     insurance
    1.04
     then
    1.02
     allowed
    1.02
    Activations Density 0.107%

    No Known Activations