© 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
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118315
    Prev
    Next
    INDEX
    Explanations

    especially inparticular

    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
    附近
    -0.07
     nearby
    -0.07
    附近的
    -0.06
     স্থানীয়
    -0.06
    旁的
    -0.06
    environnement
    -0.06
     передви
    -0.06
     दूर
    -0.06
     located
    -0.06
     அந்த
    -0.06
    POSITIVE LOGITS
     Especially
    0.08
    Especially
    0.08
     especially
    0.07
    尤其
    0.07
     szczególnie
    0.07
     Особенно
    0.06
     excepto
    0.06
    especially
    0.06
    特に
    0.06
     terutama
    0.06
    Activations Density 0.029%

    No Known Activations