© 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. 120416
    Prev
    Next
    INDEX
    Explanations

    weeks ago

    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
    iliśmy
    -0.06
     다음과
    -0.06
     সকলের
    -0.06
    所在的
    -0.06
     communicates
    -0.06
     सबै
    -0.06
     우리
    -0.05
    ؛
    -0.05
    正常的
    -0.05
     बना
    -0.05
    POSITIVE LOGITS
     excerpt
    0.06
     запи
    0.06
     hyst
    0.06
     excerpts
    0.06
     TOOLS
    0.06
     tools
    0.06
    TOOL
    0.06
     তিনিও
    0.06
     Fiction
    0.06
     ferramentas
    0.06
    Activations Density 0.036%

    No Known Activations