© 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. 130512
    Prev
    Next
    INDEX
    Explanations

    Dirac fermion, holds, Q

    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
    these
    -0.06
     festival
    -0.06
    Festival
    -0.06
    atherine
    -0.06
    These
    -0.06
     Discovery
    -0.06
     фестива
    -0.06
    asure
    -0.06
     സ
    -0.06
    щаем
    -0.05
    POSITIVE LOGITS
     agility
    0.07
     humanoid
    0.06
     доба
    0.06
     REQUI
    0.06
     дополни
    0.06
     사망
    0.06
     fatal
    0.06
     yaşam
    0.06
     вторая
    0.06
     சேர்க்க
    0.06
    Activations Density 0.001%

    No Known Activations