© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120767
    Prev
    Next
    INDEX
    Explanations

    :

    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
     lav
    -0.06
    
    -0.06
     innan
    -0.06
     peluang
    -0.06
     odyssey
    -0.06
     miesto
    -0.06
    לך
    -0.05
     একটী
    -0.05
    opportunities
    -0.05
     onları
    -0.05
    POSITIVE LOGITS
     nonprofits
    0.06
    某一
    0.06
     अलं
    0.06
    だったので
    0.06
     Flatten
    0.06
     কালের
    0.06
     sch
    0.06
    itious
    0.06
     Because
    0.06
     somewhat
    0.06
    Activations Density 0.002%

    No Known Activations