© 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. 34227
    Prev
    Next
    INDEX
    Explanations

    nuclear program development agreement

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

    cell proliferation and death

    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
    φε
    0.45
    λό
    0.45
    ξ
    0.41
    ϒ
    0.40
    Loire
    0.39
    ρε
    0.39
     Laughlin
    0.38
    Marshall
    0.38
    择
    0.38
    lover
    0.38
    POSITIVE LOGITS
     Cells
    0.61
     клеток
    0.60
    Cells
    0.58
     célula
    0.57
     клетки
    0.57
    cells
    0.54
     cell
    0.53
     Cell
    0.53
     células
    0.52
     cells
    0.52
    Activations Density 0.033%

    No Known Activations