© 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. 116792
    Prev
    Next
    INDEX
    Explanations

    code snippets and DNA terms

    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
     bacteria
    -0.06
     यामध्ये
    -0.06
     غوره
    -0.05
     llamada
    -0.05
    assigned
    -0.05
     കണ
    -0.05
     اُ
    -0.05
     পছ
    -0.05
     তৎকালীন
    -0.05
     itin
    -0.05
    POSITIVE LOGITS
     aftermath
    0.06
    ATPase
    0.06
     BY
    0.06
     president
    0.06
     harus
    0.06
    Expert
    0.06
     besten
    0.06
     இரண்டாம்
    0.06
     periodicals
    0.06
     containing
    0.05
    Activations Density 0.001%

    No Known Activations