© 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. 118285
    Prev
    Next
    INDEX
    Explanations

    friends and family

    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
     new
    -0.06
     newly
    -0.06
     verste
    -0.06
     easier
    -0.06
    europa
    -0.06
    ս
    -0.05
    lod
    -0.05
     passport
    -0.05
    tere
    -0.05
    ኚ
    -0.05
    POSITIVE LOGITS
     ماحول
    0.07
     μέσω
    0.07
     çocuk
    0.06
     Environmental
    0.06
    ຫ
    0.06
     Exactly
    0.06
    Environmental
    0.06
     Fan
    0.06
     Fighters
    0.06
     Evangelical
    0.06
    Activations Density 0.034%

    No Known Activations