© 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. 117571
    Prev
    Next
    INDEX
    Explanations

    introduction to new concepts

    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
     sort
    -0.06
     inward
    -0.06
     reiter
    -0.06
     نهاية
    -0.06
     housekeeping
    -0.06
     video
    -0.06
     регуляр
    -0.06
     regularity
    -0.06
     रिपीट
    -0.06
     видео
    -0.06
    POSITIVE LOGITS
     depriving
    0.07
     فراهم
    0.06
     માહિતી
    0.06
     deprive
    0.06
     colori
    0.06
     Inhib
    0.06
     verschill
    0.06
     कृष्ण
    0.06
     психологи
    0.06
     miejsca
    0.06
    Activations Density 0.010%

    No Known Activations