© 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. 119024
    Prev
    Next
    INDEX
    Explanations

    code start tags or identifiers

    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
     hatal
    -0.05
     MAR
    -0.05
    ["
    -0.05
     banned
    -0.05
    ("
    -0.05
     and
    -0.05
     wasted
    -0.05
    oliath
    -0.05
     Un
    -0.05
     অপেক্ষায়
    -0.05
    POSITIVE LOGITS
    Kemudian
    0.07
    Luego
    0.06
    overnment
    0.06
     चन्द्र
    0.06
     rých
    0.06
     बेसिक
    0.06
     عاملين
    0.06
     často
    0.06
     быстро
    0.06
    Clay
    0.06
    Activations Density 0.001%

    No Known Activations