© 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. 116471
    Prev
    Next
    INDEX
    Explanations

    screw fixation and bone surgery

    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
     puțin
    -0.07
     Lobby
    -0.06
     cloison
    -0.06
     वापस
    -0.06
    fonte
    -0.06
    业界
    -0.06
     इत्यादी
    -0.06
     buildings
    -0.06
     incorpor
    -0.06
     foundry
    -0.06
    POSITIVE LOGITS
     totam
    0.06
     itinerary
    0.06
     ಕ್ರಮ
    0.06
    especially
    0.06
     headquartered
    0.06
    primarily
    0.05
    辑
    0.05
    Nutrition
    0.05
     ổ
    0.05
     Chik
    0.05
    Activations Density 0.016%

    No Known Activations