© 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. 129502
    Prev
    Next
    INDEX
    Explanations

    conflict and arguments

    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
    悪
    -0.07
     harass
    -0.06
     Zeal
    -0.06
     kuin
    -0.06
    यात
    -0.05
     aggravate
    -0.05
    interactions
    -0.05
     interact
    -0.05
     tặng
    -0.05
    Int
    -0.05
    POSITIVE LOGITS
     प्रशांत
    0.06
     getValue
    0.06
     capace
    0.06
     yks
    0.06
     opaque
    0.06
    Ⅺ
    0.06
     momentary
    0.06
     viens
    0.06
     Vida
    0.06
     speechless
    0.06
    Activations Density 0.012%

    No Known Activations