© 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. 119277
    Prev
    Next
    INDEX
    Explanations

    commercial use and advertising

    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
     samego
    -0.06
    Only
    -0.06
    रविवार
    -0.06
     darkly
    -0.06
     Neighbors
    -0.06
    ễ
    -0.06
     سوم
    -0.06
     لل
    -0.06
    وص
    -0.05
    Provided
    -0.05
    POSITIVE LOGITS
     зробити
    0.06
     বললে
    0.06
     Mose
    0.06
     sucesivamente
    0.06
    াইয়া
    0.06
     сделать
    0.05
     Alcan
    0.05
     Raila
    0.05
     gern
    0.05
    璇
    0.05
    Activations Density 0.001%

    No Known Activations