© 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. 116439
    Prev
    Next
    INDEX
    Explanations

    Transanal, automated, Aqua

    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
    MACHINE
    -0.06
     resten
    -0.06
     arit
    -0.06
     beaucoup
    -0.06
    ิล
    -0.06
    Externe
    -0.06
    Interesting
    -0.06
     essas
    -0.06
     विवेकानंद
    -0.06
     satirical
    -0.06
    POSITIVE LOGITS
    eny
    0.06
    '.
    0.06
     Expl
    0.05
     discussions
    0.05
    aud
    0.05
    ოვნ
    0.05
     которым
    0.05
     விரி
    0.05
     Española
    0.05
     egent
    0.05
    Activations Density 0.001%

    No Known Activations