© 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. 116654
    Prev
    Next
    INDEX
    Explanations

    steroid, diabetes, motors, printers, observations, powders

    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
    ographer
    -0.06
     последних
    -0.06
     Últ
    -0.06
     hairy
    -0.06
    而在
    -0.06
     wines
    -0.06
    Coverage
    -0.06
     faktisk
    -0.06
    อย่างไร
    -0.05
     hatt
    -0.05
    POSITIVE LOGITS
     여기에
    0.07
     realised
    0.06
     ጉ
    0.06
     kesehatan
    0.06
    以及
    0.06
     complesso
    0.06
    ซิต
    0.06
     viaggi
    0.06
    enges
    0.06
     realized
    0.05
    Activations Density 0.085%

    No Known Activations