© 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. 119269
    Prev
    Next
    INDEX
    Explanations

    from X to Y

    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
     before
    -0.08
     njih
    -0.07
    Before
    -0.07
     πριν
    -0.07
     antes
    -0.07
    BEFORE
    -0.06
     그러
    -0.06
     יי
    -0.06
     januari
    -0.06
     helps
    -0.06
    POSITIVE LOGITS
     ወይም
    0.08
    ↵↵↵↵↵
    0.06
     หรือ
    0.06
     किंवा
    0.06
     όμως
    0.06
     다만
    0.06
     eller
    0.06
    דת
    0.06
     ಅಥವಾ
    0.06
     või
    0.06
    Activations Density 0.002%

    No Known Activations