© 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. 118384
    Prev
    Next
    INDEX
    Explanations

    Service desktop lib command options

    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
     using
    -0.06
     for
    -0.06
     famil
    -0.06
     Textile
    -0.06
     textile
    -0.06
     {
    -0.05
    会在
    -0.05
     ಒಳ್ಳೆಯ
    -0.05
    newUser
    -0.05
     bylaws
    -0.05
    POSITIVE LOGITS
    Becoming
    0.07
     pondering
    0.06
     আলাদা
    0.06
    अंतर
    0.06
     enhance
    0.06
     focus
    0.06
     közvet
    0.06
    相关的
    0.06
     more
    0.06
     калі
    0.06
    Activations Density 0.003%

    No Known Activations