© 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-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 130956
    Prev
    Next
    INDEX
    Explanations

    reopened

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Umsetzung
    -0.07
     இரண்டு
    -0.07
     podle
    -0.06
     sofort
    -0.06
     कॅम्प
    -0.06
     automatiquement
    -0.06
     two
    -0.06
     imediatamente
    -0.06
     implementation
    -0.06
     Immediately
    -0.06
    POSITIVE LOGITS
     mostrando
    0.08
     showing
    0.07
    uture
    0.06
     calon
    0.06
     shows
    0.06
     scheint
    0.06
    shows
    0.06
     repeatedly
    0.06
     attracting
    0.06
     berharap
    0.06
    Activations Density 0.009%

    No Known Activations