© 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. 117187
    Prev
    Next
    INDEX
    Explanations

    news, features, interviews, reviews, stories, analysis, advice, research, gossip

    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
     doub
    -0.06
     doubted
    -0.06
    dd
    -0.06
     छल
    -0.05
     skeptic
    -0.05
     textbook
    -0.05
    しばらく
    -0.05
     Ru
    -0.05
     Wunder
    -0.05
     generales
    -0.05
    POSITIVE LOGITS
    udor
    0.07
     efficacy
    0.06
    했지만
    0.06
     resonated
    0.06
    卻
    0.06
     buradan
    0.06
     کاربر
    0.06
     эффективности
    0.06
     Licenses
    0.06
    ք
    0.06
    Activations Density 0.012%

    No Known Activations