© 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. 119525
    Prev
    Next
    INDEX
    Explanations

    unwanted or anything

    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
     আপাত
    -0.07
    𝑆
    -0.06
    㑒
    -0.06
     multimillion
    -0.06
     mechanistic
    -0.06
    /(
    -0.06
     ():
    -0.06
     सेल्फ
    -0.05
     bewust
    -0.05
     যথাযথ
    -0.05
    POSITIVE LOGITS
     पता
    0.07
     언제
    0.07
     tới
    0.06
    一定是
    0.06
     deserves
    0.06
     لیاقت
    0.06
     can
    0.06
     می‌تواند
    0.06
     może
    0.06
     никогда
    0.06
    Activations Density 0.003%

    No Known Activations