© 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. 118321
    Prev
    Next
    INDEX
    Explanations

    eyewear and glasses

    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
    ernsey
    -0.07
     hierarchy
    -0.06
    काई
    -0.06
    ujacy
    -0.06
    水位
    -0.06
     annexation
    -0.06
     এখ
    -0.06
     hierarchical
    -0.06
     percentile
    -0.06
     Edition
    -0.05
    POSITIVE LOGITS
     sunglasses
    0.10
     glasses
    0.08
    Sunglasses
    0.08
    glasses
    0.07
     sunscreen
    0.07
     stereo
    0.07
     eyewear
    0.07
    眼鏡
    0.07
    eyeglasses
    0.07
     harmonica
    0.07
    Activations Density 0.015%

    No Known Activations