© 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. 22-GEMMASCOPE-RES-131K
    7. 74990
    Prev
    Next
    INDEX
    Explanations

    alternative method

    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
     blijven
    -1.10
    attare
    -0.93
    一定的
    -0.93
    Tembelea
    -0.93
    する場合
    -0.91
     twij
    -0.90
    zelfde
    -0.89
     risico
    -0.88
     vanske
    -0.87
    useppe
    -0.85
    POSITIVE LOGITS
     instead
    2.70
     вместо
    2.13
     invece
    2.08
     Instead
    1.92
    instead
    1.89
    Instead
    1.88
     alternative
    1.64
     istället
    1.64
     approach
    1.63
     alternatives
    1.55
    Activations Density 0.074%

    No Known Activations