© 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. 128570
    Prev
    Next
    INDEX
    Explanations

    gala, taste, Women, Brew, raise

    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
     Sebelum
    -0.07
     BEFORE
    -0.06
     énfasis
    -0.06
     DOES
    -0.06
     ইঙ্গ
    -0.06
    ပိုင်း
    -0.06
     под
    -0.06
     sebelum
    -0.05
    จะเป็น
    -0.05
     WITHOUT
    -0.05
    POSITIVE LOGITS
     grew
    0.06
     renovation
    0.06
     sistemas
    0.06
     hvert
    0.06
     wall
    0.06
     accedere
    0.06
     negotiation
    0.06
    ల్ల
    0.06
     അതിന്റെ
    0.06
     lowest
    0.06
    Activations Density 0.048%

    No Known Activations