© 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. 128285
    Prev
    Next
    INDEX
    Explanations

    document or section headers

    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
     that
    -0.07
     joven
    -0.07
    emission
    -0.06
     харак
    -0.06
     giovane
    -0.06
     جوان
    -0.06
     genders
    -0.06
     bấm
    -0.06
     measurement
    -0.06
     তিনি
    -0.06
    POSITIVE LOGITS
     Pinot
    0.08
    エリア
    0.07
     समन्वय
    0.06
     في
    0.06
     ル
    0.06
     leeway
    0.06
     ადგილ
    0.06
    လမ်း
    0.06
     Shiraz
    0.06
     Rxf
    0.06
    Activations Density 0.004%

    No Known Activations