© 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. 118024
    Prev
    Next
    INDEX
    Explanations

    place names and numbers

    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
    ดิจ
    -0.06
     स्वतंत्र
    -0.06
     discounted
    -0.06
     쓰는
    -0.06
     updater
    -0.06
    funktion
    -0.06
     censored
    -0.06
    নীতি
    -0.06
     acres
    -0.06
     Fractals
    -0.06
    POSITIVE LOGITS
     Mound
    0.06
    颓
    0.06
    week
    0.06
     pre
    0.06
    quita
    0.06
     Nachrichten
    0.06
     ഉയർന്ന
    0.05
     share
    0.05
     Dept
    0.05
     сообщение
    0.05
    Activations Density 0.022%

    No Known Activations