© 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. 128415
    Prev
    Next
    INDEX
    Explanations

    numerals and citations

    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
     prosperous
    -0.07
     delightful
    -0.07
     odyssey
    -0.07
    ỗ
    -0.06
    ILERS
    -0.06
     fraud
    -0.06
     variedade
    -0.06
    𝖙
    -0.06
     começou
    -0.06
     agony
    -0.06
    POSITIVE LOGITS
     one
    0.07
     symbolically
    0.05
    nk
    0.05
    물의
    0.05
     ie
    0.05
     особое
    0.05
     no
    0.05
    愚
    0.05
     subconsciously
    0.05
     하나의
    0.05
    Activations Density 0.006%

    No Known Activations