© 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. 107470
    Prev
    Next
    INDEX
    Explanations

    at [venue]

    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
     corrispond
    -0.96
     vara
    -0.93
     potencial
    -0.92
     economica
    -0.88
     proposito
    -0.87
     processi
    -0.87
     writing
    -0.86
     Lesnar
    -0.86
     dekorasi
    -0.85
    hatenablog
    -0.85
    POSITIVE LOGITS
    ене
    0.93
    Citizens
    0.89
     The
    0.88
    Chances
    0.87
    ům
    0.86
     éton
    0.83
    historique
    0.82
     faciles
    0.82
     великолеп
    0.80
    точници
    0.80
    Activations Density 0.058%

    No Known Activations