© 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. 128800
    Prev
    Next
    INDEX
    Explanations

    in order to

    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
     मुताबिक
    -0.07
     Bereiche
    -0.07
    äller
    -0.07
     wesentlich
    -0.06
     আরো
    -0.06
     gio
    -0.06
     dimers
    -0.06
     Chom
    -0.06
     subsets
    -0.06
     particulière
    -0.06
    POSITIVE LOGITS
    为了
    0.07
    為了
    0.07
    เพื่อให้
    0.06
     Rus
    0.06
     чтобы
    0.06
    Dc
    0.05
    ]+=
    0.05
    IDF
    0.05
    Auch
    0.05
    ப்பத
    0.05
    Activations Density 0.098%

    No Known Activations