© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119104
    Prev
    Next
    INDEX
    Explanations

    the magician

    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
     and
    -0.07
    У
    -0.06
     как
    -0.06
     и
    -0.06
     nahezu
    -0.06
     до
    -0.06
     AND
    -0.06
    及び
    -0.06
     можете
    -0.06
    बाब
    -0.06
    POSITIVE LOGITS
     already
    0.07
     a
    0.06
     consequently
    0.06
    でも
    0.06
     déjà
    0.06
    lin
    0.06
     him
    0.06
     ಪ್ರಯೋಜನ
    0.06
     respectable
    0.06
     een
    0.06
    Activations Density 0.036%

    No Known Activations