© 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. 128726
    Prev
    Next
    INDEX
    Explanations

    circular rotation and degrees

    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
     भाइयों
    -0.06
    SLICE
    -0.06
    第六
    -0.06
     gerenci
    -0.06
    getRandom
    -0.06
     bbox
    -0.06
     юго
    -0.06
     Thứ
    -0.06
     rừng
    -0.06
     diffuse
    -0.06
    POSITIVE LOGITS
     Zusammenhang
    0.06
     :
    0.06
     experiences
    0.06
    oteur
    0.06
    never
    0.06
    優れた
    0.06
     experiments
    0.06
    levels
    0.06
     Experience
    0.06
    orld
    0.06
    Activations Density 0.007%

    No Known Activations