© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129454
    Prev
    Next
    INDEX
    Explanations

    distribution and assignment

    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
     తేదీ
    -0.06
     जमानत
    -0.06
     proactive
    -0.06
     comprobar
    -0.06
     zaman
    -0.05
     terbaru
    -0.05
     टाइम
    -0.05
     populer
    -0.05
    datetime
    -0.05
     مجوز
    -0.05
    POSITIVE LOGITS
     распреде
    0.08
     توزيع
    0.08
     distributes
    0.08
     distribusi
    0.07
     distributing
    0.07
     redistributed
    0.07
     recalcul
    0.07
     distribuição
    0.07
     assigning
    0.07
     assigns
    0.07
    Activations Density 0.034%

    No Known Activations