© 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. 120049
    Prev
    Next
    INDEX
    Explanations

    days ago

    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
     टिश
    -0.06
    に
    -0.06
    ोग्रा
    -0.06
    evším
    -0.06
     ряда
    -0.06
     biri
    -0.06
    [
    -0.06
     favorable
    -0.06
    ोच्च
    -0.05
     ਨਹੀਂ
    -0.05
    POSITIVE LOGITS
     unseres
    0.06
     receitas
    0.06
     四
    0.06
     الص
    0.06
     mencipt
    0.06
     муниципа
    0.06
     正
    0.06
    ख्या
    0.06
    四
    0.06
    度假
    0.05
    Activations Density 0.004%

    No Known Activations