© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130907
    Prev
    Next
    INDEX
    Explanations

    stunts and extreme activities

    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
    我们需要
    -0.07
     crescimento
    -0.07
     низ
    -0.07
     صارفین
    -0.07
    它是
    -0.07
    ですので
    -0.07
     they
    -0.06
    ダイニング
    -0.06
     হতা
    -0.06
     bienvenidos
    -0.06
    POSITIVE LOGITS
     feats
    0.07
     risky
    0.07
     सेफ्टी
    0.07
     safety
    0.06
    Safety
    0.06
     risking
    0.06
     aerial
    0.06
     audacious
    0.06
     extraordinary
    0.06
     spectacle
    0.06
    Activations Density 0.010%

    No Known Activations