© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119051
    Prev
    Next
    INDEX
    Explanations

    commercial offers and services

    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
     such
    -0.07
     аспек
    -0.07
    例如
    -0.07
     aspekt
    -0.07
     mať
    -0.06
     eksempel
    -0.06
    Peace
    -0.06
    例えば
    -0.06
     เช่น
    -0.06
     Shaun
    -0.06
    POSITIVE LOGITS
     обоих
    0.07
     কার্ড
    0.06
     Aí
    0.06
     ambos
    0.06
     Angebote
    0.06
    今後の
    0.06
    ziff
    0.06
    offers
    0.06
    offer
    0.06
    まだ
    0.06
    Activations Density 0.001%

    No Known Activations