© 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. 128910
    Prev
    Next
    INDEX
    Explanations

    foreign languages

    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
     aina
    -0.06
     districts
    -0.06
     or
    -0.06
    These
    -0.06
    这两个
    -0.06
     такие
    -0.06
     কাউকে
    -0.06
     have
    -0.06
    Comment
    -0.06
     these
    -0.05
    POSITIVE LOGITS
     desde
    0.07
     گزشتہ
    0.07
     từ
    0.07
    lerinin
    0.06
     hvor
    0.06
    Desde
    0.06
     donde
    0.06
     여러
    0.06
     అనేక
    0.06
    です
    0.06
    Activations Density 0.014%

    No Known Activations