© 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. 129912
    Prev
    Next
    INDEX
    Explanations

    two or seven

    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
     jedoch
    -0.07
     however
    -0.06
     चाहे
    -0.06
     إلا
    -0.06
     tetapi
    -0.06
     главное
    -0.06
     tačiau
    -0.06
     Namun
    -0.06
    疑惑
    -0.06
     Via
    -0.06
    POSITIVE LOGITS
     hoa
    0.07
     يعني
    0.07
     nontrivial
    0.07
     (!)
    0.07
     dozens
    0.07
     совершенно
    0.06
    だけで
    0.06
     fairly
    0.06
     довольно
    0.06
     реа
    0.06
    Activations Density 0.023%

    No Known Activations