© 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. 119570
    Prev
    Next
    INDEX
    Explanations

    links and URLs

    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
     این
    -0.07
     resilient
    -0.06
     نروح
    -0.06
    मांड
    -0.06
    ここで
    -0.06
     هذه
    -0.06
     keepsake
    -0.06
    <0x8F>
    -0.06
    更に
    -0.06
     فرنسا
    -0.06
    POSITIVE LOGITS
     because
    0.08
     their
    0.08
     несмотря
    0.07
    的原因
    0.06
    因素
    0.06
     despite
    0.06
    Their
    0.06
    ("**
    0.06
     Meinung
    0.06
     Exceptions
    0.06
    Activations Density 0.025%

    No Known Activations