© 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. 129547
    Prev
    Next
    INDEX
    Explanations

    different types or languages

    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
     collega
    -0.06
    accept
    -0.06
     accept
    -0.06
     μέσω
    -0.06
    Mal
    -0.06
     assurances
    -0.06
     hopeful
    -0.05
     что
    -0.05
     Mal
    -0.05
     tahun
    -0.05
    POSITIVE LOGITS
     разных
    0.07
     different
    0.07
     Different
    0.07
     разнови
    0.06
    这个时候
    0.06
     diferentes
    0.06
    Different
    0.06
     നിങ്ങളുടെ
    0.06
     வெவ்வேறு
    0.06
    different
    0.06
    Activations Density 0.001%

    No Known Activations