© 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. 117245
    Prev
    Next
    INDEX
    Explanations

    structurally conserved, homologous, distinct, diverse, analogous

    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
     etc
    -0.06
     સહિત
    -0.06
     etcétera
    -0.06
     including
    -0.06
     cazul
    -0.06
    方式
    -0.06
    ়
    -0.06
    Vertices
    -0.06
    including
    -0.06
    )।
    -0.06
    POSITIVE LOGITS
    чів
    0.06
    ផ្តល់
    0.06
     निर्णायक
    0.06
     memang
    0.06
     পরিমাণে
    0.06
    Но
    0.06
                      
    0.06
    Ad
    0.06
     ribbed
    0.05
    াবাদ
    0.05
    Activations Density 0.024%

    No Known Activations