© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 80925
    Prev
    Next
    INDEX
    Explanations

    legal and constitutional rights

    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
     Erfahrungen
    -0.81
     dryer
    -0.78
     dangereux
    -0.77
    𖧵
    -0.75
     célèbres
    -0.75
    steamcommunity
    -0.75
     ills
    -0.74
    applicable
    -0.71
     noblest
    -0.71
    Vier
    -0.71
    POSITIVE LOGITS
     justification
    1.17
     required
    1.12
     basis
    1.09
     requirement
    1.03
     reasons
    1.02
     permission
    1.02
     definition
    1.00
     mechanism
    0.98
     requirements
    0.98
     recognition
    0.97
    Activations Density 0.041%

    No Known Activations