© 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. 116403
    Prev
    Next
    INDEX
    Explanations

    integral calculus

    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
     στα
    -0.06
    もあります
    -0.06
     અને
    -0.06
     kanyang
    -0.06
     নজর
    -0.06
     этой
    -0.06
     הוא
    -0.06
    utim
    -0.05
     कम्प
    -0.05
     his
    -0.05
    POSITIVE LOGITS
     latest
    0.06
     complained
    0.06
    聋
    0.06
     sonrası
    0.06
     роз
    0.06
     initiator
    0.06
    ไป
    0.06
     ensuing
    0.05
    她们
    0.05
     lamented
    0.05
    Activations Density 0.004%

    No Known Activations