© 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. 117407
    Prev
    Next
    INDEX
    Explanations

    http links

    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
    等を
    -0.07
    now
    -0.06
    等が
    -0.06
    Ahora
    -0.06
    getting
    -0.06
    登记
    -0.06
    ："
    -0.06
     必ず
    -0.06
     Теперь
    -0.06
     terão
    -0.06
    POSITIVE LOGITS
    ()
    0.06
    一种
    0.06
     wilde
    0.06
     subdivision
    0.05
     பயன்படுத்தி
    0.05
     characteristics
    0.05
     छोटे
    0.05
     http
    0.05
    تھی
    0.05
    嬰
    0.05
    Activations Density 0.042%

    No Known Activations