© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118140
    Prev
    Next
    INDEX
    Explanations

    case choice disagreement venue

    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
     এতদিন
    -0.06
     ഇപ്പോൾ
    -0.06
    Euler
    -0.06
     pohyb
    -0.06
    iphatic
    -0.06
    Peak
    -0.06
    Persistent
    -0.06
     প্রাথম
    -0.06
     restricting
    -0.06
     uko
    -0.06
    POSITIVE LOGITS
     فهو
    0.07
     choice
    0.07
     izbor
    0.06
    叹
    0.06
     случай
    0.06
    嘆
    0.06
     venue
    0.06
    这位
    0.06
    женный
    0.06
     выбора
    0.06
    Activations Density 0.031%

    No Known Activations