© 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. 116855
    Prev
    Next
    INDEX
    Explanations

    notes, end, special, propellers, step

    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
     supposed
    -0.06
    本来
    -0.06
     supposedly
    -0.06
     کیسے
    -0.06
    需要在
    -0.06
     aparent
    -0.06
    nine
    -0.06
    ieri
    -0.06
     новий
    -0.06
     лоша
    -0.06
    POSITIVE LOGITS
     любую
    0.06
     اطراف
    0.06
    êtres
    0.06
     frighten
    0.06
     any
    0.06
    也沒有
    0.06
    NOS
    0.06
    rosis
    0.06
     любого
    0.06
     दट
    0.06
    Activations Density 0.003%

    No Known Activations