© 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. 116892
    Prev
    Next
    INDEX
    Explanations

    made in the USA

    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
     mạnh
    -0.08
     자유
    -0.07
     malé
    -0.07
    蝦
    -0.07
    自由
    -0.07
     freely
    -0.07
     강력
    -0.07
     analisi
    -0.06
     свобо
    -0.06
     recklessly
    -0.06
    POSITIVE LOGITS
     (+
    0.07
     ("
    0.06
                          
    0.05
     @
    0.05
     название
    0.05
     अनेक
    0.05
    SIAN
    0.05
     "
    0.05
     gestation
    0.05
    ("
    0.05
    Activations Density 0.005%

    No Known Activations