© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130891
    Prev
    Next
    INDEX
    Explanations

    Lus

    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
     arguably
    -0.06
     нефте
    -0.06
     UIT
    -0.06
     Stunde
    -0.06
     reliably
    -0.06
    OrFail
    -0.06
     hardly
    -0.05
     correspondents
    -0.05
     Grenzen
    -0.05
     என்றும்
    -0.05
    POSITIVE LOGITS
     기념
    0.06
    🌰
    0.06
     racional
    0.06
    योगी
    0.06
     hideous
    0.06
     atunci
    0.06
    Ки
    0.06
     internazionali
    0.06
    ucius
    0.06
    理性
    0.05
    Activations Density 0.020%

    No Known Activations