© 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. 119577
    Prev
    Next
    INDEX
    Explanations

    accession numbers and Q&A patterns

    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
     это
    -0.06
     হওয়ায়
    -0.06
     প্রতিহিংস
    -0.06
     this
    -0.06
     እየ
    -0.06
     VFX
    -0.06
     vecinos
    -0.06
     вже
    -0.06
     खूप
    -0.05
    브
    -0.05
    POSITIVE LOGITS
     country
    0.07
    length
    0.06
    先
    0.06
     length
    0.06
    所谓
    0.06
    };
    0.06
     nacionales
    0.06
     připoj
    0.06
    LANGUAGE
    0.06
    溌
    0.06
    Activations Density 0.001%

    No Known Activations