© 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. 116131
    Prev
    Next
    INDEX
    Explanations

    legal terms and 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
    adona
    -0.06
     어떤
    -0.06
     nevertheless
    -0.06
     ምን
    -0.06
     více
    -0.06
     starken
    -0.06
     svært
    -0.06
    異なります
    -0.06
     twenty
    -0.06
     verwendeten
    -0.06
    POSITIVE LOGITS
    。
    0.06
     précédente
    0.06
    itatea
    0.05
    ႇ
    0.05
    ースト
    0.05
     τό
    0.05
     ঘোষনা
    0.05
    jek
    0.05
    shield
    0.05
     Çünkü
    0.05
    Activations Density 0.001%

    No Known Activations