© 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. 197262
    Prev
    Next
    INDEX
    Explanations

    after "promises"

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

    tracking flight status

    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
     naudoj
    0.53
     समित
    0.52
     usamos
    0.51
     intraven
    0.50
     réussi
    0.49
     о
    0.48
     змен
    0.48
     aiuta
    0.47
     lavoro
    0.47
     हानिकारक
    0.47
    POSITIVE LOGITS
    ным
    0.49
    гова
    0.49
    的项目
    0.48
     Tourism
    0.46
    ব
    0.46
    ainkan
    0.45
    蚬
    0.45
    তের
    0.43
    Tourism
    0.43
    ：
    0.43
    Activations Density 0.004%

    No Known Activations