© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2692
    Prev
    Next
    INDEX
    Explanations

    medical treatments and recovery

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

    medical treatment

    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_53_width_65k_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
    顐
    0.42
    伨
    0.40
     สื
    0.39
    uzzo
    0.38
     ډاونلوډ
    0.36
    ângulo
    0.35
     अडचणी
    0.35
    㧡
    0.35
    ⴹ
    0.35
     Bege
    0.35
    POSITIVE LOGITS
     treatment
    4.75
    treatment
    4.47
     Treatment
    4.41
    Treatment
    4.41
     treatments
    4.31
     TREATMENT
    4.22
     tratamiento
    4.13
     tratamento
    3.97
     Treatments
    3.97
    治療
    3.92
    Activations Density 0.476%

    No Known Activations