© 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. 128657
    Prev
    Next
    INDEX
    Explanations

    contribute to organizations

    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
     expliquer
    -0.07
    露出
    -0.06
    Sexy
    -0.06
    如果没有
    -0.06
     architectures
    -0.06
     тъ
    -0.06
     drugs
    -0.06
     realistic
    -0.05
     Spawn
    -0.05
     जरूरतों
    -0.05
    POSITIVE LOGITS
    作業
    0.06
     воспита
    0.06
     gladly
    0.06
     diye
    0.06
     yardımcı
    0.06
    чыць
    0.06
    different
    0.06
     volunteer
    0.06
     Pflicht
    0.06
     Garant
    0.06
    Activations Density 0.032%

    No Known Activations