© 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. 119669
    Prev
    Next
    INDEX
    Explanations

    4-bit architecture identifiers

    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
     devenit
    -0.06
     noble
    -0.06
     বিজনেস
    -0.06
    篇文章
    -0.06
    কাশ
    -0.06
    Everything
    -0.06
     alles
    -0.06
     വ്യക്ത
    -0.06
     গভীর
    -0.06
     आत
    -0.06
    POSITIVE LOGITS
    anzi
    0.06
     Гос
    0.06
     déco
    0.06
    sila
    0.06
     ≈
    0.06
     примерно
    0.06
     casi
    0.05
     रुका
    0.05
    केवल
    0.05
     použí
    0.05
    Activations Density 0.002%

    No Known Activations