© 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. 128874
    Prev
    Next
    INDEX
    Explanations

    places, countries, states, and companies

    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
     Им
    -0.06
    കളും
    -0.06
     অর্থাৎ
    -0.06
    只有
    -0.06
     Norton
    -0.06
     அது
    -0.06
    会
    -0.06
     अजि
    -0.06
     Vien
    -0.06
    филь
    -0.06
    POSITIVE LOGITS
    的主要
    0.06
     মেরামত
    0.06
     types
    0.06
     principali
    0.06
     places
    0.06
     principales
    0.06
     फ्लावर
    0.06
     大
    0.06
     संकट
    0.06
     পেরিয়ে
    0.06
    Activations Density 0.003%

    No Known Activations