© 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. 120675
    Prev
    Next
    INDEX
    Explanations

    M- shock waves

    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
     ऑपरेशन
    -0.06
     జిల్లా
    -0.06
     symbolized
    -0.06
     subroutine
    -0.06
     tougher
    -0.06
     plag
    -0.06
     IEC
    -0.06
     comes
    -0.06
     (%
    -0.06
    东方
    -0.06
    POSITIVE LOGITS
     আজ
    0.06
    ೀಯ
    0.06
    เรา
    0.06
     शुर
    0.06
    ものを
    0.06
    雰囲
    0.06
    ?
    0.06
    ായത്
    0.06
    内容
    0.05
     અમે
    0.05
    Activations Density 0.005%

    No Known Activations