© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 128206
    Prev
    Next
    INDEX
    Explanations

    measurement units and codes

    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
     το
    -0.07
     impacts
    -0.06
     sepanjang
    -0.06
     menjadikan
    -0.06
     দুটি
    -0.06
     its
    -0.06
     never
    -0.05
    
    -0.05
     तहे
    -0.05
     федера
    -0.05
    POSITIVE LOGITS
     қо
    0.07
     حقیقی
    0.06
    gy
    0.06
    很多的
    0.06
    yg
    0.06
     kobi
    0.06
    注意
    0.06
    涀
    0.06
     größer
    0.06
    🔬
    0.06
    Activations Density 0.009%

    No Known Activations