© 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. 119975
    Prev
    Next
    INDEX
    Explanations

    foreign language 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
     disorders
    -0.06
     geschaffen
    -0.06
     disorder
    -0.06
     المعروف
    -0.06
     を
    -0.06
    abra
    -0.06
     কাজকর্ম
    -0.06
     disciples
    -0.06
     dimaksud
    -0.06
    ini
    -0.05
    POSITIVE LOGITS
     dwóch
    0.06
     ৬
    0.06
     äußerst
    0.06
     तीन
    0.06
     på
    0.06
     ১০
    0.06
     générateur
    0.06
     três
    0.06
     în
    0.06
     auf
    0.06
    Activations Density 0.001%

    No Known Activations