© 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. 130253
    Prev
    Next
    INDEX
    Explanations

    corporation and others

    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
     (
    -0.06
       
    -0.06
     каждая
    -0.05
     воспользова
    -0.05
    ius
    -0.05
     realizando
    -0.05
         
    -0.05
     φ
    -0.05
     осуществля
    -0.05
    ที่เรา
    -0.05
    POSITIVE LOGITS
     incompat
    0.07
     ძალიან
    0.07
     серьез
    0.07
     має
    0.06
     have
    0.06
     çok
    0.06
     can
    0.06
     Skype
    0.06
    椅子
    0.06
     सैन्य
    0.06
    Activations Density 0.002%

    No Known Activations