© 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. 130056
    Prev
    Next
    INDEX
    Explanations

    different styles and types

    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
     п
    -0.07
    }-\
    -0.06
     Gesamt
    -0.06
    全体の
    -0.06
     समग्र
    -0.06
    Mature
    -0.06
     použ
    -0.06
     оно
    -0.06
     Mature
    -0.06
     mature
    -0.06
    POSITIVE LOGITS
     electronically
    0.07
     différents
    0.07
    sense
    0.07
     different
    0.06
     various
    0.06
     Various
    0.06
     BLACK
    0.06
     sense
    0.06
     বিভিন্ন
    0.06
     ulike
    0.06
    Activations Density 0.002%

    No Known Activations