© 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. 26189
    Prev
    Next
    INDEX
    Explanations

    weighs approximately

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

    plants and orchids

    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
    苙
    0.46
     chickens
    0.44
     fluvial
    0.43
     nutritive
    0.42
     floc
    0.41
     turkeys
    0.40
    糁
    0.40
     fgets
    0.40
    鱸
    0.40
     প্রতির
    0.39
    POSITIVE LOGITS
     orchid
    0.57
     orchids
    0.55
     Aeonium
    0.51
     Orchid
    0.51
    eonium
    0.47
    拍卖
    0.45
    🌵
    0.42
     Cactus
    0.41
     potted
    0.41
    orchid
    0.41
    Activations Density 0.066%

    No Known Activations