© 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. 131047
    Prev
    Next
    INDEX
    Explanations

    Company names, corporations, legal entities

    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
     মজুম
    -0.07
     appel
    -0.06
     ಸಮಸ್ಯ
    -0.06
    डा
    -0.06
     росій
    -0.06
     scheint
    -0.06
     सतर्क
    -0.06
     appels
    -0.06
     संबंधों
    -0.06
     რუს
    -0.05
    POSITIVE LOGITS
     purposefully
    0.08
     constructed
    0.07
     aside
    0.06
     сразу
    0.06
     доба
    0.06
     systematically
    0.06
     routinely
    0.06
     might
    0.06
     intentionally
    0.06
     HAD
    0.06
    Activations Density 0.009%

    No Known Activations