© 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. 129992
    Prev
    Next
    INDEX
    Explanations

    each

    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
     at
    -0.06
     اعتراض
    -0.06
     دام
    -0.06
    Dog
    -0.06
    🃏
    -0.06
     on
    -0.06
     Ducati
    -0.06
     also
    -0.06
    🦄
    -0.06
    两天
    -0.05
    POSITIVE LOGITS
    each
    0.08
     каждая
    0.08
     chacune
    0.08
     każdy
    0.07
     each
    0.07
     fiecare
    0.07
     każ
    0.07
     každý
    0.07
    Each
    0.07
    それぞれの
    0.07
    Activations Density 0.001%

    No Known Activations