© 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. 120365
    Prev
    Next
    INDEX
    Explanations

    s

    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
     நண்ப
    -0.07
    REVIEW
    -0.07
    这么
    -0.06
    这样的
    -0.06
    highest
    -0.06
     eighties
    -0.06
     이런
    -0.06
     personagem
    -0.06
    這麼
    -0.06
     વખ
    -0.06
    POSITIVE LOGITS
     తెలి
    0.06
     Thursday
    0.06
     ya
    0.06
    从小
    0.06
    Couldn
    0.06
     hustle
    0.06
     Friday
    0.06
    Castle
    0.06
     kinda
    0.05
     Couldn
    0.05
    Activations Density 0.071%

    No Known Activations