© 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. 39432
    Prev
    Next
    INDEX
    Explanations

    estimate specifications

    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
     époux
    -1.10
     demandent
    -0.97
    俢
    -0.93
     tomber
    -0.91
    Suma
    -0.88
     levier
    -0.88
    Текст
    -0.88
     Tienen
    -0.87
     caído
    -0.87
     transmite
    -0.87
    POSITIVE LOGITS
     To
    0.92
     EST
    0.90
     estimate
    0.87
     In
    0.86
     est
    0.83
     Ign
    0.82
     transport
    0.82
     estimated
    0.81
     choose
    0.80
     A
    0.79
    Activations Density 0.112%

    No Known Activations