© 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. 119284
    Prev
    Next
    INDEX
    Explanations

    allocating, using, or defining limits

    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
     также
    -0.06
     also
    -0.06
     também
    -0.06
     presumably
    -0.05
    ვის
    -0.05
     marries
    -0.05
    Sp
    -0.05
    Our
    -0.05
     cintura
    -0.05
     probably
    -0.05
    POSITIVE LOGITS
    孱
    0.06
     வளர்ச்சி
    0.06
    😺
    0.06
    限制
    0.06
     desarrollo
    0.06
     revisar
    0.06
    ﾁ
    0.06
     $)
    0.06
     Interviews
    0.06
    并非
    0.06
    Activations Density 0.001%

    No Known Activations