© 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. 116961
    Prev
    Next
    INDEX
    Explanations

    ribs, topics, knot, mid, Client, graft

    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
    dependent
    -0.07
     Shorts
    -0.07
     রক্তাক্ত
    -0.06
     రక్త
    -0.06
     قصير
    -0.06
    ნ
    -0.06
    dent
    -0.06
     Hose
    -0.06
    arah
    -0.06
     may
    -0.06
    POSITIVE LOGITS
    显然
    0.06
     nies
    0.06
    失
    0.06
     የቀ
    0.06
    単純
    0.06
     получаем
    0.06
    解决方案
    0.06
     Posted
    0.06
    йо
    0.05
     заяви
    0.05
    Activations Density 0.001%

    No Known Activations