© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117447
    Prev
    Next
    INDEX
    Explanations

    words starting with It

    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
     육
    -0.07
    육
    -0.06
     repent
    -0.06
    ําน
    -0.06
     ಅವ
    -0.06
    umpang
    -0.06
     satisfies
    -0.06
     சட்டமன்ற
    -0.06
     없음
    -0.06
     obey
    -0.06
    POSITIVE LOGITS
     બાળકો
    0.06
    щих
    0.06
    就會
    0.06
     toepassing
    0.06
     會
    0.06
     पीछ
    0.06
     사람은
    0.06
     регулярно
    0.05
    かれた
    0.05
    國
    0.05
    Activations Density 0.065%

    No Known Activations