© 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. 116998
    Prev
    Next
    INDEX
    Explanations

    software licenses and URLs

    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
     are
    -0.07
     merupakan
    -0.06
     is
    -0.06
     can
    -0.06
    rent
    -0.06
     willingness
    -0.06
    こそ
    -0.06
     Putra
    -0.06
     adalah
    -0.06
     have
    -0.06
    POSITIVE LOGITS
     которая
    0.07
    which
    0.06
     koja
    0.06
     which
    0.06
    㚼
    0.06
     Особенно
    0.06
     случи
    0.06
     移動
    0.06
    ที่ไม่
    0.06
     wyb
    0.06
    Activations Density 0.017%

    No Known Activations