© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 116680
    Prev
    Next
    INDEX
    Explanations

    questions starting with how

    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
    ۞
    -0.06
     گی
    -0.06
     bandwidth
    -0.06
     telah
    -0.06
     være
    -0.06
     প্রচলিত
    -0.06
     আজকে
    -0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.06
     funktion
    -0.06
    ↵↵↵
    -0.06
    POSITIVE LOGITS
    🙁
    0.06
     više
    0.06
    也没有
    0.06
     how
    0.06
     desperate
    0.06
    pflege
    0.06
    也没
    0.06
     justa
    0.05
     the
    0.05
    其实
    0.05
    Activations Density 0.006%

    No Known Activations