© 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. 119027
    Prev
    Next
    INDEX
    Explanations

    ship names or dates

    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
    那些
    -0.06
     Those
    -0.06
     основных
    -0.06
    Those
    -0.06
     वर्तमान
    -0.06
     fue
    -0.06
     MOVE
    -0.06
     füh
    -0.06
     mivel
    -0.06
     with
    -0.06
    POSITIVE LOGITS
    sometimes
    0.07
     occasionally
    0.07
     occasional
    0.07
     geleg
    0.07
    Occasionally
    0.07
     diversas
    0.07
    种种
    0.07
     glitches
    0.06
     sometimes
    0.06
     accidentally
    0.06
    Activations Density 0.001%

    No Known Activations