© 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. 129355
    Prev
    Next
    INDEX
    Explanations

    years of imprisonment or life sentence

    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
    собенно
    -0.06
     emergency
    -0.06
    ToBase
    -0.05
     énerg
    -0.05
    themem
    -0.05
     pomocą
    -0.05
     furono
    -0.05
     revoke
    -0.05
     הם
    -0.05
     особенно
    -0.05
    POSITIVE LOGITS
    或者
    0.07
    もしくは
    0.07
    enty
    0.07
     वर्णन
    0.07
    accio
    0.07
     could
    0.07
     may
    0.07
     hoặc
    0.06
     opportunities
    0.06
     ወይም
    0.06
    Activations Density 0.002%

    No Known Activations