© 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. 130929
    Prev
    Next
    INDEX
    Explanations

    bool type attributes

    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
     can
    -0.11
     could
    -0.08
     dapat
    -0.08
     può
    -0.08
     können
    -0.08
     aún
    -0.08
     میتوان
    -0.07
     можем
    -0.07
    できます
    -0.07
    したいと思います
    -0.07
    POSITIVE LOGITS
    通常の
    0.06
     دعم
    0.06
     சிலர்
    0.06
    رفع
    0.06
    当時の
    0.05
    வந்த
    0.05
     সহ্য
    0.05
     lieu
    0.05
     normalement
    0.05
    慣
    0.05
    Activations Density 0.002%

    No Known Activations