© 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. 117209
    Prev
    Next
    INDEX
    Explanations

    wood shelving, installation needs, book services, receive urinary, drunk driving

    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
     gồm
    -0.06
     ακόμα
    -0.06
     شامل
    -0.06
    原创
    -0.06
     فيها
    -0.06
    包括
    -0.06
    RAchievement
    -0.06
    各式
    -0.06
     звуча
    -0.06
     totalité
    -0.06
    POSITIVE LOGITS
     eerste
    0.06
     donc
    0.06
     zeer
    0.06
     the
    0.06
     in
    0.06
     primeira
    0.06
     In
    0.06
     Therefore
    0.06
     provides
    0.06
    Tit
    0.06
    Activations Density 0.001%

    No Known Activations