© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 120334
    Prev
    Next
    INDEX
    Explanations

    strict comparison or control

    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
     monstrous
    -0.06
    pik
    -0.06
    只好
    -0.06
     गलती
    -0.06
     joins
    -0.06
     கருத்து
    -0.06
     Plas
    -0.06
     நீர
    -0.06
     ধারণা
    -0.06
     ostensibly
    -0.06
    POSITIVE LOGITS
     nacionales
    0.06
     Conform
    0.06
    Follow
    0.06
     follow
    0.05
     nationalists
    0.05
     Automat
    0.05
     অসহ
    0.05
     музи
    0.05
    enabled
    0.05
     ninety
    0.05
    Activations Density 0.058%

    No Known Activations