© 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. 116574
    Prev
    Next
    INDEX
    Explanations

    Summary: This, More than

    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
     automatically
    -0.06
    నాలు
    -0.06
     automatisch
    -0.06
    aying
    -0.06
    hou
    -0.06
     Mikhail
    -0.05
     ;
    -0.05
    <h2>
    -0.05
    োয়
    -0.05
    ),
    -0.05
    POSITIVE LOGITS
    เกม
    0.07
    记忆
    0.06
     seni
    0.06
    數字
    0.06
     geändert
    0.06
     숫
    0.06
     खेत
    0.06
     diminu
    0.06
    ={'
    0.06
     renowned
    0.06
    Activations Density 0.010%

    No Known Activations