© 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. 120408
    Prev
    Next
    INDEX
    Explanations

    shared, Shared

    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
     obecnie
    -0.06
     metodología
    -0.06
    shut
    -0.06
     Involved
    -0.06
     psychiatry
    -0.06
     encircled
    -0.06
     neoclassical
    -0.06
     લખ
    -0.06
    idelity
    -0.05
     själ
    -0.05
    POSITIVE LOGITS
    shared
    0.07
     shared
    0.07
    Shared
    0.06
    collisions
    0.06
     Belediye
    0.06
    SHARED
    0.06
     combattre
    0.06
     Trip
    0.06
    那么
    0.06
     Shared
    0.06
    Activations Density 0.008%

    No Known Activations