© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6488
    Prev
    Next
    INDEX
    Explanations

    parts of plants, flowers, buds, leaves

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

    plant reproductive parts and foliage

    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_53_width_65k_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
    脚步
    0.54
     প্রজাত
    0.53
     территория
    0.52
     የግ
    0.52
    堣
    0.51
     стаби
    0.50
     громадян
    0.49
    alım
    0.48
     туда
    0.48
    逘
    0.48
    POSITIVE LOGITS
     bract
    1.09
     buds
    1.03
     ovary
    0.96
     ovaries
    0.89
     bud
    0.85
     capsules
    0.84
     pods
    0.84
     petals
    0.83
     capsule
    0.80
     abort
    0.77
    Activations Density 0.072%

    No Known Activations