© 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. 120662
    Prev
    Next
    INDEX
    Explanations

    axis, around, about

    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
     prelude
    -0.06
    脂
    -0.06
     as
    -0.06
     potenz
    -0.06
     terminating
    -0.06
     deseo
    -0.06
     WANT
    -0.06
     mayonnaise
    -0.06
    broom
    -0.06
     tenei
    -0.06
    POSITIVE LOGITS
    不僅
    0.06
    不仅
    0.06
     הח
    0.06
     gaat
    0.06
     また
    0.06
     rollercoaster
    0.06
     แบ่ง
    0.06
     छोटी
    0.06
     보겠습니다
    0.06
    European
    0.06
    Activations Density 0.003%

    No Known Activations