© 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. 117286
    Prev
    Next
    INDEX
    Explanations

    sample code or remote data

    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
    称号
    -0.06
     behaved
    -0.06
     серд
    -0.06
    arine
    -0.06
     déliv
    -0.05
    ground
    -0.05
     қу
    -0.05
     전에
    -0.05
     kneeling
    -0.05
    굶
    -0.05
    POSITIVE LOGITS
    巨大
    0.08
     massive
    0.07
     devido
    0.07
     massively
    0.06
     огром
    0.06
     hardly
    0.06
     hauptsächlich
    0.06
     colossal
    0.06
    巨大的
    0.06
     głównie
    0.06
    Activations Density 0.009%

    No Known Activations