© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 120283
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code variables

    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
    所以
    -0.06
     নিয়েই
    -0.06
     coincide
    -0.06
    "}}>
    -0.06
     make
    -0.06
     所以
    -0.06
    るので
    -0.06
     hedef
    -0.06
     so
    -0.05
     மக்களை
    -0.05
    POSITIVE LOGITS
     iets
    0.08
     จาก
    0.06
    一切
    0.06
     stiffer
    0.06
     écoles
    0.06
     відповід
    0.06
    كنولوج
    0.06
    नातील
    0.06
     কট
    0.06
    तन
    0.06
    Activations Density 0.001%

    No Known Activations