© 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. 117675
    Prev
    Next
    INDEX
    Explanations

    section beginnings or separators

    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
     from
    -0.06
     मर्ज
    -0.06
     பொருள்
    -0.06
     सर्जन
    -0.06
     in
    -0.06
    English
    -0.06
     until
    -0.05
     पढ़ते
    -0.05
    erase
    -0.05
     Until
    -0.05
    POSITIVE LOGITS
     나의
    0.07
     دیوار
    0.07
     его
    0.07
     propósito
    0.06
     основных
    0.06
     Gegenwart
    0.06
     jeho
    0.06
     setCurrent
    0.06
    ホテル
    0.06
    但我
    0.06
    Activations Density 0.016%

    No Known Activations