© 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. 200924
    Prev
    Next
    INDEX
    Explanations

    Best, ideal, mesh, School, test

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

    structure of atoms

    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
     arm
    0.49
    涔
    0.46
     qualifying
    0.45
     Qualifying
    0.44
    ’
    0.44
     hours
    0.44
    補
    0.42
    CAN
    0.42
     decrease
    0.41
     lactation
    0.41
    POSITIVE LOGITS
     Иң
    0.52
     считает
    0.52
     নিয়েছে
    0.51
    словия
    0.51
    ())){
    0.51
     முன்னாள்
    0.50
    avacan
    0.50
     zaidi
    0.50
     übernimmt
    0.50
     стране
    0.48
    Activations Density 0.000%

    No Known Activations