© 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. 117076
    Prev
    Next
    INDEX
    Explanations

    code or data related logic

    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
     weitere
    -0.07
     další
    -0.07
     ভবিষ্যতে
    -0.07
    更に
    -0.07
    下一步
    -0.07
    又
    -0.07
     weer
    -0.06
    进一步
    -0.06
     또
    -0.06
     essentiellement
    -0.06
    POSITIVE LOGITS
    ាញ់
    0.07
     Gemä
    0.06
     দখল
    0.06
     Jeśli
    0.06
     gdy
    0.06
     armor
    0.06
     Nod
    0.06
     чове
    0.06
     until
    0.05
     अगर
    0.05
    Activations Density 0.002%

    No Known Activations