© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 130956
    Prev
    Next
    INDEX
    Explanations

    Q: and an event

    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
     gyerek
    -1.08
     stratég
    -1.07
     abril
    -1.03
     ſtand
    -1.02
     elefante
    -1.02
     Polícia
    -0.98
     trimestre
    -0.97
     restaurantes
    -0.95
     támogat
    -0.94
     chico
    -0.94
    POSITIVE LOGITS
    3
    1.15
    7
    1.11
     direito
    1.10
    w
    1.04
     lia
    1.01
    h
    1.01
    (":");
    1.00
    Peso
    0.99
    k
    0.98
    ai
    0.98
    Activations Density 0.000%

    No Known Activations