© 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. 119967
    Prev
    Next
    INDEX
    Explanations

    plants and their characteristics

    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
    Các
    -0.07
     jednotliv
    -0.07
    ikiem
    -0.07
     със
    -0.06
     hefty
    -0.06
     análise
    -0.06
    ēc
    -0.06
     впли
    -0.06
     selecion
    -0.06
    ulz
    -0.06
    POSITIVE LOGITS
     farming
    0.06
     used
    0.06
     agron
    0.06
     my
    0.06
     if
    0.06
    园
    0.06
    ondale
    0.05
     employed
    0.05
     производ
    0.05
    farming
    0.05
    Activations Density 0.008%

    No Known Activations