© 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. 116781
    Prev
    Next
    INDEX
    Explanations

    color names and related words

    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
     استعمال
    -0.07
     to
    -0.07
     soweit
    -0.06
    ⤠
    -0.06
     műkö
    -0.06
     экзем
    -0.06
     sonuç
    -0.06
     utiliser
    -0.06
     такому
    -0.06
    യുള്ള
    -0.06
    POSITIVE LOGITS
    bane
    0.06
     the
    0.06
    等你
    0.06
     vuol
    0.06
     developments
    0.06
     Alfred
    0.06
     nuances
    0.06
     নানা
    0.05
     natomiast
    0.05
       
    0.05
    Activations Density 0.015%

    No Known Activations