© 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. 119310
    Prev
    Next
    INDEX
    Explanations

    through places

    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
    違う
    -0.07
     from
    -0.07
    其他
    -0.06
     kutoka
    -0.06
    อื่นๆ
    -0.06
     innych
    -0.06
     других
    -0.06
     مشابه
    -0.06
    从
    -0.06
    其他的
    -0.06
    POSITIVE LOGITS
     often
    0.07
     Often
    0.06
     can
    0.06
     Einwilligung
    0.06
    شان
    0.06
    Often
    0.06
     лабора
    0.06
    appar
    0.06
     strongly
    0.06
     highly
    0.06
    Activations Density 0.009%

    No Known Activations