© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 129720
    Prev
    Next
    INDEX
    Explanations

    a new

    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
     раздра
    -0.06
     বলেছিল
    -0.06
     প্রবেশ
    -0.06
    même
    -0.06
     superb
    -0.06
     लगाएंगे
    -0.06
     interestingly
    -0.05
    weird
    -0.05
     สร้าง
    -0.05
     coalesce
    -0.05
    POSITIVE LOGITS
     this
    0.11
     tejto
    0.08
     هذا
    0.08
     এই
    0.08
    この
    0.08
     этого
    0.08
     această
    0.08
     този
    0.08
     इस
    0.07
     این
    0.07
    Activations Density 0.186%

    No Known Activations