© 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. 129897
    Prev
    Next
    INDEX
    Explanations

    short codes or identifiers

    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
     ocorr
    -0.07
     tanpa
    -0.06
     auditory
    -0.06
     Đấy
    -0.06
    遇到的
    -0.06
     তাকে
    -0.06
     Effectively
    -0.06
     그걸
    -0.06
    context
    -0.06
     তাঁকে
    -0.06
    POSITIVE LOGITS
     بهذه
    0.06
    phrase
    0.06
     보자
    0.06
     peux
    0.05
     gunakan
    0.05
     بهذا
    0.05
    Wah
    0.05
     biodiesel
    0.05
    を使用
    0.05
     utilizzando
    0.05
    Activations Density 0.004%

    No Known Activations