© 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. 118419
    Prev
    Next
    INDEX
    Explanations

    HTML tags and code snippets

    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
     особен
    -0.07
     бывшего
    -0.07
     gồm
    -0.06
     Failed
    -0.06
     comprising
    -0.06
     Means
    -0.06
    Hundreds
    -0.06
    สวย
    -0.06
     красивая
    -0.06
     sepan
    -0.06
    POSITIVE LOGITS
     J
    0.06
     வைக்க
    0.06
     causa
    0.06
    ᅩ
    0.06
     ସ
    0.06
    imple
    0.06
     यूनिट
    0.05
     constitutional
    0.05
     お
    0.05
     removal
    0.05
    Activations Density 0.001%

    No Known Activations