© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 16594
    Prev
    Next
    INDEX
    Explanations

    names with middle initial J

    np_acts-logits-general · gemini-2.5-flash-lite

    LaTeX alignment environments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Peachtree
    0.42
    猿
    0.41
    ంబ
    0.39
    现在的
    0.39
     Nw
    0.39
    ্লি
    0.38
     ৃ
    0.38
    മാ
    0.38
    製の
    0.38
    காற்று
    0.38
    POSITIVE LOGITS
     &=\
    0.57
    would
    0.50
     would
    0.49
     যেত
    0.49
     WOULD
    0.49
     &
    0.48
     &=&
    0.48
    &=
    0.45
    &=\
    0.45
     &=
    0.43
    Activations Density 0.006%

    No Known Activations