© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117972
    Prev
    Next
    INDEX
    Explanations

    LC

    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
     lovable
    -0.07
     ஏராளமான
    -0.07
    เหล่า
    -0.06
     bygone
    -0.06
     прекра
    -0.06
     halted
    -0.06
    NuGet
    -0.06
    掛
    -0.06
    女性
    -0.06
     আবারো
    -0.06
    POSITIVE LOGITS
     yield
    0.06
    で
    0.06
    的一个
    0.05
     erfolgre
    0.05
     Successfully
    0.05
     bằng
    0.05
     simulate
    0.05
     mencoba
    0.05
     Wale
    0.05
     Vergleich
    0.05
    Activations Density 0.001%

    No Known Activations