© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119122
    Prev
    Next
    INDEX
    Explanations

    git status changes detached

    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
     service
    -0.07
     customer
    -0.07
    security
    -0.06
    มาตรฐาน
    -0.06
     servicing
    -0.06
     security
    -0.06
     standards
    -0.06
     Sicherheit
    -0.06
     Sicherheits
    -0.06
    迎来
    -0.06
    POSITIVE LOGITS
    lug
    0.06
     preparing
    0.06
    盖
    0.06
    Preparing
    0.06
     cubre
    0.06
     preparação
    0.06
    alles
    0.06
     préparation
    0.05
     preparando
    0.05
    📎
    0.05
    Activations Density 0.009%

    No Known Activations