© 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. 119377
    Prev
    Next
    INDEX
    Explanations

    introductionchangesshareschönburg

    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
    Anyways
    -0.06
    kitt
    -0.06
    就可以了
    -0.06
    就可以
    -0.06
    णु
    -0.06
    ecto
    -0.06
     nouvel
    -0.06
    *%
    -0.06
     newbie
    -0.05
     Helene
    -0.05
    POSITIVE LOGITS
     era
    0.06
    ましたが
    0.06
     дости
    0.06
     reach
    0.06
    エイ
    0.06
     whereas
    0.05
     whereby
    0.05
     reached
    0.05
     hvor
    0.05
    ்சை
    0.05
    Activations Density 0.003%

    No Known Activations