© 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. 128685
    Prev
    Next
    INDEX
    Explanations

    Russian criminal tattoo

    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
    既に
    -0.06
    PLIED
    -0.06
     Eventually
    -0.06
     unbound
    -0.06
    ራስ
    -0.06
     fatig
    -0.05
     रिवाज
    -0.05
    ternal
    -0.05
     kendi
    -0.05
    BCD
    -0.05
    POSITIVE LOGITS
    waterslide
    0.06
     цієї
    0.06
     accurate
    0.06
     Bunun
    0.06
     exclusivity
    0.06
     Valeria
    0.06
     predator
    0.06
    ^{+}
    0.06
    wię
    0.06
     verifiable
    0.06
    Activations Density 0.001%

    No Known Activations