© 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. 118371
    Prev
    Next
    INDEX
    Explanations

    exactly what is happening

    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
     অনেক
    -0.06
     most
    -0.06
     максимально
    -0.06
     supposedly
    -0.06
     melodies
    -0.06
    都是
    -0.06
    的基本
    -0.06
     really
    -0.06
     methamphetamine
    -0.05
     अधिकांश
    -0.05
    POSITIVE LOGITS
     exactly
    0.11
     exactamente
    0.10
     esattamente
    0.10
    exactly
    0.09
     exatamente
    0.09
     precisely
    0.09
     exactement
    0.09
     Exactly
    0.09
     precisamente
    0.08
     genau
    0.08
    Activations Density 0.009%

    No Known Activations