© 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. 117199
    Prev
    Next
    INDEX
    Explanations

    the start of lists or sentences

    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
     everything
    -0.06
     प्योर
    -0.06
     வகையான
    -0.06
     awning
    -0.06
     trademark
    -0.06
    Jupiter
    -0.06
     yazı
    -0.06
    ཤ
    -0.06
    ClNO
    -0.06
     maximal
    -0.06
    POSITIVE LOGITS
    లుగు
    0.06
     নেয়
    0.06
     then
    0.06
    dou
    0.06
    複雑
    0.06
     pitting
    0.06
     Berikut
    0.06
     одному
    0.05
    すると
    0.05
     최근
    0.05
    Activations Density 0.001%

    No Known Activations