© 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. 18367
    Prev
    Next
    INDEX
    Explanations

    bees, honey, hive

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

    honey and bee products

    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
    ეცი
    0.44
    हरे
    0.44
    ("/"))
    0.43
    oppel
    0.42
    녈
    0.42
     상승
    0.41
    пой
    0.41
    鯨
    0.41
    FBSDKApp
    0.40
     जरूरतों
    0.40
    POSITIVE LOGITS
    🍯
    1.18
    🐝
    1.17
     bees
    1.15
     honey
    1.09
    蜂蜜
    1.07
     hives
    1.06
     hive
    1.05
     Bees
    1.04
     beeh
    1.02
     Honey
    1.00
    Activations Density 0.038%

    No Known Activations