© 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. 198264
    Prev
    Next
    INDEX
    Explanations

    airport and related concepts

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

    mission validation

    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
    はん
    0.51
    реги
    0.51
    Игра
    0.49
    жды
    0.48
    ｪ
    0.48
    WithOwner
    0.48
    𝘞
    0.47
    Ре
    0.47
    лан
    0.46
     решать
    0.46
    POSITIVE LOGITS
     pter
    0.58
     airport
    0.49
     carpeting
    0.48
     ornament
    0.48
     endocrine
    0.45
     canonical
    0.45
     tattoos
    0.44
     tattooing
    0.44
     canon
    0.44
     import
    0.44
    Activations Density 0.001%

    No Known Activations