© 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. 120073
    Prev
    Next
    INDEX
    Explanations

    names and foreign script

    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
     black
    -0.07
     cacti
    -0.06
    black
    -0.06
    STATS
    -0.06
    神秘
    -0.06
     disen
    -0.06
    ट्स
    -0.06
    黑
    -0.06
     vượt
    -0.06
    करना
    -0.06
    POSITIVE LOGITS
     two
    0.07
    থানি
    0.06
    Promise
    0.06
     neutrophil
    0.06
     iki
    0.06
    ［
    0.06
    两大
    0.06
     दोन
    0.06
     incompetent
    0.06
     clumsy
    0.06
    Activations Density 0.012%

    No Known Activations