© 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. 116789
    Prev
    Next
    INDEX
    Explanations

    mafia, mob, gangster

    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
    を下
    -0.06
     자주
    -0.06
     salv
    -0.06
     thường
    -0.06
     Jays
    -0.06
    habitude
    -0.06
     ერთ
    -0.06
     친구
    -0.06
    equipped
    -0.06
     anarch
    -0.06
    POSITIVE LOGITS
     new
    0.07
     استف
    0.06
     eyebrows
    0.06
     dainty
    0.06
     elegance
    0.06
     elegant
    0.06
    优雅
    0.06
     physician
    0.06
    acja
    0.06
     wool
    0.06
    Activations Density 0.004%

    No Known Activations