© 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. 117164
    Prev
    Next
    INDEX
    Explanations

    package cm, Product Description

    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
    同样
    -0.07
     pasajeros
    -0.06
    
    -0.06
     właścic
    -0.06
     hız
    -0.06
    貪
    -0.06
     biraz
    -0.06
     puzzled
    -0.06
     Embora
    -0.06
     পাবলিক
    -0.06
    POSITIVE LOGITS
     관련된
    0.06
     [
    0.06
     K
    0.06
    (
    0.06
    Ly
    0.05
     dahulu
    0.05
    に関する
    0.05
     set
    0.05
     ك
    0.05
     Don
    0.05
    Activations Density 0.001%

    No Known Activations