© 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. 82851
    Prev
    Next
    INDEX
    Explanations

    persons to whom

    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
     allows
    -0.94
     includes
    -0.93
     hundreds
    -0.91
     allowing
    -0.90
     their
    -0.87
     taking
    -0.86
     required
    -0.85
     more
    -0.85
     most
    -0.84
     help
    -0.84
    POSITIVE LOGITS
    pping
    0.95
    
    0.93
     <",
    0.92
     يصل
    0.89
    Listed
    0.86
    ViewBag
    0.86
    filed
    0.86
    この
    0.85
    whose
    0.84
     SECOND
    0.84
    Activations Density 0.008%

    No Known Activations