© 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. 130632
    Prev
    Next
    INDEX
    Explanations

    titles and organizations

    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
     allerede
    -0.08
     which
    -0.07
     sudah
    -0.07
    क्यों
    -0.07
     why
    -0.07
     already
    -0.06
    why
    -0.06
     in
    -0.06
     уже
    -0.06
     इन
    -0.06
    POSITIVE LOGITS
     yanında
    0.06
    WebDriver
    0.06
     killing
    0.05
     heavenly
    0.05
     dextrose
    0.05
     számára
    0.05
     অমৃত
    0.05
     tweeted
    0.05
     mysterious
    0.05
     vanligt
    0.05
    Activations Density 0.001%

    No Known Activations