© 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. 130220
    Prev
    Next
    INDEX
    Explanations

    same X

    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
     still
    -0.07
     vẫn
    -0.07
    依然
    -0.07
     tetap
    -0.07
     modified
    -0.07
     ਦਿੱ
    -0.06
    역시
    -0.06
    やはり
    -0.06
     verschill
    -0.06
     upgraded
    -0.06
    POSITIVE LOGITS
     to
    0.07
     as
    0.07
     как
    0.07
    ೈನ
    0.06
     ১৪
    0.06
     kultury
    0.06
     in
    0.06
     with
    0.06
     viele
    0.06
     on
    0.06
    Activations Density 0.030%

    No Known Activations