© 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. 118892
    Prev
    Next
    INDEX
    Explanations

    data and related information

    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
    ç
    -0.05
    any
    -0.05
     Ber
    -0.05
    same
    -0.05
    possible
    -0.05
    विच
    -0.05
    inherit
    -0.05
     encountered
    -0.05
     any
    -0.05
    če
    -0.05
    POSITIVE LOGITS
     genellikle
    0.07
     настолько
    0.06
     ಉತ್ತಮ
    0.06
     elég
    0.06
     SELECT
    0.06
    かなり
    0.06
     recouvert
    0.06
     CAST
    0.06
     incluindo
    0.06
     Biografie
    0.06
    Activations Density 0.004%

    No Known Activations