© 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. 128341
    Prev
    Next
    INDEX
    Explanations

    Home

    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
     hacerlo
    -0.06
     결방
    -0.06
     programs
    -0.06
     Derived
    -0.06
     Memory
    -0.06
     derived
    -0.05
    programs
    -0.05
    protocols
    -0.05
     yalnız
    -0.05
     несколь
    -0.05
    POSITIVE LOGITS
    術
    0.07
     señala
    0.06
     grot
    0.06
    ธิบาย
    0.06
     விளக்க
    0.06
     অধিকাংশ
    0.06
     глав
    0.06
     argument
    0.06
     រ
    0.06
    抱怨
    0.06
    Activations Density 0.004%

    No Known Activations