© 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. 119580
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    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
     However
    -0.07
    :
    -0.06
    Here
    -0.06
    之前的
    -0.06
     cách
    -0.06
    在一
    -0.06
     individually
    -0.06
     Ih
    -0.06
     individu
    -0.06
     वहीं
    -0.06
    POSITIVE LOGITS
     edit
    0.06
     არის
    0.06
     ـ
    0.06
     grievance
    0.06
     assailant
    0.06
     জাপান
    0.06
    Newsletter
    0.06
    真的很
    0.06
    <0xAD>
    0.06
     아무
    0.06
    Activations Density 0.005%

    No Known Activations