© 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. 128746
    Prev
    Next
    INDEX
    Explanations

    safety, uses, or related concepts

    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
     procedente
    -0.06
    regener
    -0.06
     regener
    -0.06
     announcing
    -0.06
     ნ
    -0.06
     nowego
    -0.06
     certifies
    -0.06
     средне
    -0.06
    மண
    -0.06
    You
    -0.06
    POSITIVE LOGITS
     safety
    0.07
     all
    0.07
     사용하여
    0.07
    安全的
    0.07
    afety
    0.06
     एग्रीकल्चर
    0.06
     безпе
    0.06
     Verwendung
    0.06
    safety
    0.06
     безопас
    0.06
    Activations Density 0.004%

    No Known Activations