© 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. 116481
    Prev
    Next
    INDEX
    Explanations

    code comments and page titles

    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
     öğrend
    -0.06
     нар
    -0.06
    blr
    -0.06
     unseres
    -0.06
    DEPARTMENT
    -0.06
    ঈ
    -0.06
     Alumni
    -0.06
     komplett
    -0.06
     ಯಾವಾಗ
    -0.05
     intenso
    -0.05
    POSITIVE LOGITS
     वोट
    0.07
     designed
    0.07
     உள்ப
    0.06
     unjustified
    0.06
     mainly
    0.06
     Spieler
    0.06
     stated
    0.06
    designed
    0.06
    stated
    0.06
     เขา
    0.06
    Activations Density 0.002%

    No Known Activations