© 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. 97983
    Prev
    Next
    INDEX
    Explanations

    giving or receiving things

    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
    āda
    -0.99
     ผม
    -0.94
    }:{
    -0.88
    irà
    -0.86
     générer
    -0.85
     recém
    -0.84
    🈷
    -0.83
    cosas
    -0.82
    flavor
    -0.82
     swojego
    -0.82
    POSITIVE LOGITS
     scope
    1.04
     recruits
    0.96
    タオル
    0.92
     shelter
    0.91
     implements
    0.88
     funds
    0.88
     by
    0.87
     facilities
    0.87
     from
    0.86
    scope
    0.86
    Activations Density 0.018%

    No Known Activations