© 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. 117420
    Prev
    Next
    INDEX
    Explanations

    analysis and assessment methods

    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
     완성
    -0.07
     আমাকে
    -0.07
     完成
    -0.06
     එක්
    -0.06
     completing
    -0.06
     final
    -0.06
    完成
    -0.06
     completed
    -0.06
    email
    -0.06
     interim
    -0.06
    POSITIVE LOGITS
     analysis
    0.08
     análise
    0.08
     análisis
    0.08
     analisi
    0.08
     spectral
    0.07
    analysis
    0.07
    Analysis
    0.07
    analisi
    0.07
     analyzing
    0.07
     indicadores
    0.07
    Activations Density 0.014%

    No Known Activations