© 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. 129899
    Prev
    Next
    INDEX
    Explanations

    names and places

    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
     interracial
    -0.07
     racial
    -0.06
    カラー
    -0.06
    rear
    -0.06
     색
    -0.06
     cowardly
    -0.06
    主持
    -0.05
    ឧប
    -0.05
    urally
    -0.05
    ards
    -0.05
    POSITIVE LOGITS
    没什么
    0.07
    Grande
    0.06
     놓고
    0.06
     వీరి
    0.06
     licking
    0.06
    螞
    0.06
     finder
    0.06
    
    0.06
     Gourmet
    0.06
    ('_
    0.06
    Activations Density 0.047%

    No Known Activations