© 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. 128760
    Prev
    Next
    INDEX
    Explanations

    language fragments

    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
     substitutions
    -0.07
     separable
    -0.07
     conformément
    -0.06
    zték
    -0.06
     according
    -0.06
     Öz
    -0.06
     quelconque
    -0.06
     ভয়ঙ্কর
    -0.06
     kend
    -0.06
     distinctive
    -0.06
    POSITIVE LOGITS
     larger
    0.07
    large
    0.07
     Large
    0.06
     large
    0.06
     multimillion
    0.06
     overgrown
    0.06
     মতামত
    0.06
    Large
    0.06
     exempel
    0.05
     예를
    0.05
    Activations Density 0.001%

    No Known Activations