© 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. 118805
    Prev
    Next
    INDEX
    Explanations

    hydrophobic portions

    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
    जिस
    -0.07
     являются
    -0.07
    偶尔
    -0.06
    ottam
    -0.06
     intestine
    -0.06
     находятся
    -0.06
     olvidar
    -0.06
    ሞች
    -0.06
     begle
    -0.06
     కనిప
    -0.06
    POSITIVE LOGITS
     procedimentos
    0.06
    ,
    0.05
    ↵
    0.05
    oooo
    0.05
    open
    0.05
     digit
    0.05
     듯
    0.05
     而
    0.05
     అభిమా
    0.05
     kelu
    0.05
    Activations Density 0.001%

    No Known Activations