© 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. 116690
    Prev
    Next
    INDEX
    Explanations

    creating shortcuts and launchers

    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
     контроли
    -0.07
     volled
    -0.07
     impeccable
    -0.06
     barric
    -0.06
     undeniable
    -0.06
    ✔
    -0.06
     uninterrupted
    -0.06
     Nordic
    -0.06
     блоки
    -0.06
     televised
    -0.06
    POSITIVE LOGITS
     этим
    0.06
    を作成
    0.06
     Тем
    0.06
    决策
    0.06
     Maker
    0.05
    ],[
    0.05
     oregano
    0.05
    作成
    0.05
     fabri
    0.05
     this
    0.05
    Activations Density 0.009%

    No Known Activations