© 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. 119807
    Prev
    Next
    INDEX
    Explanations

    including items and kinds

    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
     বিক্ষ
    -0.07
     what
    -0.06
    複雜
    -0.06
    ']).
    -0.06
     super
    -0.06
     특별
    -0.06
     جاي
    -0.06
     afirmou
    -0.06
     Với
    -0.06
     özel
    -0.06
    POSITIVE LOGITS
     bezieht
    0.07
     includes
    0.07
     encompasses
    0.06
     inanimate
    0.06
    对了
    0.06
    までの
    0.06
    مراجع
    0.06
    包含
    0.06
    CLUDING
    0.06
     успеха
    0.06
    Activations Density 0.022%

    No Known Activations