© 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. 119146
    Prev
    Next
    INDEX
    Explanations

    idealized version

    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
     bày
    -0.05
     Baroque
    -0.05
     বাংলাদেশে
    -0.05
    PAIR
    -0.05
    이렇게
    -0.05
     literalmente
    -0.05
     Contemporary
    -0.05
    ···
    -0.05
    ›
    -0.05
     föl
    -0.05
    POSITIVE LOGITS
     idealized
    0.07
     அளவு
    0.07
    等を
    0.07
     ट्वी
    0.06
    heroes
    0.06
    Heroes
    0.06
    濾
    0.06
    理想
    0.06
    രുടെയും
    0.06
    も見
    0.06
    Activations Density 0.027%

    No Known Activations