© 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. 117242
    Prev
    Next
    INDEX
    Explanations

    lists using etc

    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
    कामा
    -0.07
     και
    -0.07
    க்கூட
    -0.07
     после
    -0.07
     রয়েছে
    -0.07
     अॅ
    -0.07
    与
    -0.07
    與
    -0.07
     ដែល
    -0.07
    နှင့်
    -0.07
    POSITIVE LOGITS
    today
    0.05
     گردش
    0.05
     spotless
    0.05
     awfully
    0.05
     aggressively
    0.05
     ভদ্র
    0.05
     intuition
    0.05
    vej
    0.05
     verhindern
    0.05
     powodu
    0.05
    Activations Density 0.008%

    No Known Activations