© 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. 116227
    Prev
    Next
    INDEX
    Explanations

    must-have / should / definitely / try

    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
     require
    -0.07
     therefore
    -0.06
     hence
    -0.06
     pesky
    -0.06
    ల
    -0.06
     sostanz
    -0.06
     consequently
    -0.05
     more
    -0.05
     wymaga
    -0.05
    телей
    -0.05
    POSITIVE LOGITS
     zeker
    0.08
    Definitely
    0.08
    無視
    0.07
     sicuramente
    0.07
    Finally
    0.07
    ようやく
    0.07
     zouden
    0.07
    絶対に
    0.06
    必定
    0.06
     pulsing
    0.06
    Activations Density 0.024%

    No Known Activations