© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 203474
    Prev
    Next
    INDEX
    Explanations

    code and math symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ,
    0.42
     Sho
    0.37
     Out
    0.35
     Producers
    0.35
     Artifact
    0.35
     CLT
    0.35
     Products
    0.35
     Two
    0.35
     _,
    0.34
     ,,
    0.34
    POSITIVE LOGITS
    ánchez
    0.46
     ಅವರ
    0.45
     მათი
    0.43
     त्यांनी
    0.41
    herme
    0.39
     በእ
    0.37
     তিনিও
    0.37
     mortem
    0.37
     ನಾನು
    0.36
    цыі
    0.36
    Activations Density 0.094%

    No Known Activations