© 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. 130414
    Prev
    Next
    INDEX
    Explanations

    license and free software

    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
     to
    -0.07
    Bei
    -0.06
     is
    -0.06
    ப்படுத்தும்
    -0.06
     ?,
    -0.05
     लिया
    -0.05
    வர்களின்
    -0.05
     atténuées
    -0.05
    ㅊ
    -0.05
    Current
    -0.05
    POSITIVE LOGITS
     eclipsed
    0.06
     apex
    0.06
    之间
    0.06
    競争
    0.06
    大多
    0.06
     игре
    0.06
     tenacious
    0.06
    就像
    0.06
     despite
    0.06
    แต่
    0.06
    Activations Density 0.006%

    No Known Activations