© 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. 129183
    Prev
    Next
    INDEX
    Explanations

    seasons and weather conditions

    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
    lection
    -0.07
     lähe
    -0.06
     ABOVE
    -0.06
     castle
    -0.06
     stately
    -0.06
     ближе
    -0.06
     когда
    -0.06
    ').
    -0.06
    知名
    -0.06
    世界上
    -0.06
    POSITIVE LOGITS
     contienen
    0.06
     may
    0.05
    こちらも
    0.05
     seventh
    0.05
     flimsy
    0.05
     unitary
    0.05
     する
    0.05
     Penang
    0.05
    。...
    0.05
     हेल्प
    0.05
    Activations Density 0.004%

    No Known Activations