© 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. 116808
    Prev
    Next
    INDEX
    Explanations

    Johnny Rodriguez

    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
     quatro
    -0.07
     taxonomy
    -0.06
     délic
    -0.06
    流域
    -0.06
     terreno
    -0.06
     discíp
    -0.06
    ρό
    -0.06
     القسم
    -0.06
    ດ້ວຍ
    -0.06
    uzzi
    -0.06
    POSITIVE LOGITS
    نما
    0.06
     代表
    0.06
     Thus
    0.06
     Earlier
    0.05
    кот
    0.05
     Representative
    0.05
     সফ
    0.05
     Valid
    0.05
    losen
    0.05
     عدة
    0.05
    Activations Density 0.001%

    No Known Activations