© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 11040
    Prev
    Next
    INDEX
    Explanations

    asthma and respiratory treatments

    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_31_width_65k_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
     hepatocellular
    0.50
    legraph
    0.42
    醐
    0.42
    javase
    0.41
     लोहा
    0.40
    Specular
    0.40
    阳光
    0.39
     tattooing
    0.39
    hull
    0.39
     radiometric
    0.39
    POSITIVE LOGITS
     asthma
    1.18
     Asthma
    1.07
     inhal
    0.90
     COPD
    0.84
     bronchial
    0.81
     pulmonary
    0.80
     bronchitis
    0.79
    哮
    0.78
     respiratory
    0.78
     inhaled
    0.78
    Activations Density 0.032%

    No Known Activations