© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130590
    Prev
    Next
    INDEX
    Explanations

    voter fraud

    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
     showing
    -0.07
     Showing
    -0.07
    她
    -0.07
    Showing
    -0.07
    你的
    -0.06
    彼女
    -0.06
     trovato
    -0.06
     mostrando
    -0.06
     mucho
    -0.06
     أنها
    -0.06
    POSITIVE LOGITS
    atil
    0.06
    綸
    0.06
     ordenar
    0.06
     hierarch
    0.06
     निशान
    0.06
     கொ
    0.05
     kinds
    0.05
    ண்ப
    0.05
     December
    0.05
    菅
    0.05
    Activations Density 0.019%

    No Known Activations