© 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. 130618
    Prev
    Next
    INDEX
    Explanations

    v

    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
     hommage
    -0.06
     разных
    -0.06
     quase
    -0.06
     huge
    -0.06
     hampir
    -0.06
     aqui
    -0.06
     på
    -0.06
     HUGE
    -0.06
     here
    -0.06
     Aqui
    -0.06
    POSITIVE LOGITS
    上述
    0.06
     therefore
    0.06
    个月
    0.06
     Therefore
    0.06
     deliber
    0.06
     particular
    0.05
    個月
    0.05
     pretože
    0.05
    Therefore
    0.05
     ".
    0.05
    Activations Density 0.001%

    No Known Activations