© 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. 117469
    Prev
    Next
    INDEX
    Explanations

    cylindrical objects and extended limbs

    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
     знает
    -0.06
     اکبر
    -0.06
     Satan
    -0.06
    タイル
    -0.05
    一半
    -0.05
    aham
    -0.05
    ény
    -0.05
     época
    -0.05
    Stopped
    -0.05
    sdag
    -0.05
    POSITIVE LOGITS
    bodyParser
    0.07
     genotyping
    0.06
     प्री
    0.06
    宠物
    0.06
    ുകൊ
    0.06
     piccoli
    0.06
     తాగ
    0.06
     użytk
    0.06
     small
    0.06
     someplace
    0.06
    Activations Density 0.032%

    No Known Activations