© 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. 117425
    Prev
    Next
    INDEX
    Explanations

    solar cells, silicon, oxide

    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
     Sometimes
    -0.06
     Garland
    -0.06
     paranoia
    -0.06
     dấu
    -0.06
     পাওয়
    -0.06
     Alpes
    -0.06
     persoane
    -0.06
    llium
    -0.06
     which
    -0.05
     something
    -0.05
    POSITIVE LOGITS
    ोजा
    0.07
     forgiving
    0.07
     musí
    0.06
     kobiet
    0.06
    umenical
    0.06
    Zimbabwe
    0.06
    youtube
    0.06
     žena
    0.06
     aider
    0.06
     aiding
    0.06
    Activations Density 0.002%

    No Known Activations