© 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. 119073
    Prev
    Next
    INDEX
    Explanations

    question / technical command

    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
     telas
    -0.07
     během
    -0.07
     coleção
    -0.06
     geot
    -0.06
     weight
    -0.06
     trials
    -0.06
     reactivation
    -0.06
    甭
    -0.06
     beach
    -0.06
    carotene
    -0.06
    POSITIVE LOGITS
     двор
    0.07
     servis
    0.06
    ষ্ঠান
    0.06
    Competition
    0.06
    ressive
    0.06
    北京市
    0.06
     ঘরের
    0.06
     Cosby
    0.06
    决赛
    0.06
    versing
    0.06
    Activations Density 0.002%

    No Known Activations