© 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. 130224
    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
     a
    -0.07
     an
    -0.06
     til
    -0.06
    invest
    -0.06
    ようになって
    -0.06
     demi
    -0.06
       
    -0.06
     till
    -0.05
     ఇంకా
    -0.05
     thêm
    -0.05
    POSITIVE LOGITS
    能够在
    0.06
     avaient
    0.06
    czyć
    0.06
     Requires
    0.06
     Rowland
    0.06
    您
    0.06
    эта
    0.06
     كبيرة
    0.06
     avevano
    0.06
     রাসূল
    0.06
    Activations Density 0.006%

    No Known Activations