© 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. 116300
    Prev
    Next
    INDEX
    Explanations

    question or answer post

    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
     then
    -0.07
     ability
    -0.06
     Tues
    -0.06
     সাধারণ
    -0.06
    Then
    -0.06
     প্রশিক্ষ
    -0.06
    तेरे
    -0.06
     Then
    -0.05
     shortly
    -0.05
     Fäh
    -0.05
    POSITIVE LOGITS
     животных
    0.07
     at
    0.07
     a
    0.07
     ones
    0.07
    separate
    0.06
    撑
    0.06
     animals
    0.06
     in
    0.06
     separate
    0.06
     Vicki
    0.06
    Activations Density 0.011%

    No Known Activations