© 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. 119398
    Prev
    Next
    INDEX
    Explanations

    rock band

    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
     exercices
    -0.07
     எப்போதும்
    -0.06
    trusted
    -0.06
     அவரின்
    -0.06
     trusted
    -0.06
     frail
    -0.06
     ಮತ್ತೆ
    -0.06
     fieles
    -0.06
     scept
    -0.06
     bequest
    -0.06
    POSITIVE LOGITS
     нашем
    0.07
     接
    0.06
    しよう
    0.06
     вполне
    0.06
    hots
    0.06
    となる
    0.06
     досить
    0.06
     думаю
    0.06
    EnableWeb
    0.06
     opravdu
    0.06
    Activations Density 0.011%

    No Known Activations