© 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. 119325
    Prev
    Next
    INDEX
    Explanations

    scale =

    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
     concise
    -0.07
    android
    -0.07
     তাপমাত্রা
    -0.06
     misma
    -0.06
     unn
    -0.06
    だけに
    -0.06
     actresses
    -0.06
    瞄
    -0.06
     onderste
    -0.06
    inflate
    -0.06
    POSITIVE LOGITS
     Charity
    0.06
    เป็น
    0.06
    rush
    0.06
    죵
    0.06
    Generally
    0.06
    కాల
    0.06
     বৈদেশিক
    0.06
     फ़ोन
    0.05
    খিল
    0.05
    Everyone
    0.05
    Activations Density 0.001%

    No Known Activations