© 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. 52719
    Prev
    Next
    INDEX
    Explanations

    tuberculosis and TB

    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
     trigger
    0.40
     drowned
    0.38
     port
    0.38
     événement
    0.38
    ાર્
    0.38
     hydroly
    0.38
     grab
    0.38
    銚
    0.37
     recharge
    0.36
     torrential
    0.36
    POSITIVE LOGITS
     Tuberculosis
    0.85
     tuberculosis
    0.83
     TB
    0.75
     tuberculous
    0.73
    TB
    0.67
     tubercul
    0.63
     tuberc
    0.62
     Mycobacterium
    0.61
     tubercles
    0.60
     tubercle
    0.58
    Activations Density 0.014%

    No Known Activations