© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 17818
    Prev
    Next
    INDEX
    Explanations

    flight cancellations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soever
    1.05
    ;
    1.05
    ların
    1.03
    ).
    1.02
    ),
    1.02
    рование
    0.98
    ור
    0.96
    вається
    0.95
    も
    0.94
    нула
    0.93
    POSITIVE LOGITS
     Cancellation
    0.86
    .
    0.81
     After
    0.80
    h
    0.78
     U
    0.78
     For
    0.78
     canceled
    0.77
    in
    0.74
    дят
    0.73
     Then
    0.72
    Activations Density 0.002%

    No Known Activations