© 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. 129489
    Prev
    Next
    INDEX
    Explanations

    Arnab, shoot out, Molecular screening

    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
     другая
    -0.07
     другой
    -0.07
    сюда
    -0.06
    裡面
    -0.06
     another
    -0.06
    नए
    -0.06
     ಪ್ರತ
    -0.06
    another
    -0.06
     विरोध
    -0.06
     andere
    -0.06
    POSITIVE LOGITS
     (
    0.07
     начну
    0.06
     더욱
    0.06
    㭐
    0.06
     Z
    0.06
     Ai
    0.06
    㒵
    0.06
    更是
    0.06
    j
    0.06
     }\
    0.06
    Activations Density 0.002%

    No Known Activations