© 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. 138623
    Prev
    Next
    INDEX
    Explanations

    planting plants and flowers

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

    planting seeds or trees

    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
    された
    0.44
     ধরিয়
    0.44
     públic
    0.43
     demás
    0.43
     cámara
    0.43
     پڑے
    0.43
    滝
    0.42
    玖
    0.41
     crédito
    0.41
    事物
    0.41
    POSITIVE LOGITS
    donor
    0.49
    report
    0.46
     embeds
    0.46
    diabetes
    0.45
    Donor
    0.45
    Elect
    0.45
    planting
    0.45
     ड्रीम
    0.44
    planted
    0.44
    Tile
    0.44
    Activations Density 0.004%

    No Known Activations