© 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. 12960
    Prev
    Next
    INDEX
    Explanations

    medical diagnoses and related conditions

    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
    .;
    0.35
    ρεύ
    0.34
    ("");
    0.31
    ("
    0.30
     чыныгы
    0.30
    ("--
    0.29
     maxLength
    0.29
    '{
    0.29
     подоб
    0.29
     थिए
    0.29
    POSITIVE LOGITS
     neoplasms
    0.32
    Configs
    0.32
     fertilization
    0.31
    თან
    0.31
     وس
    0.31
    sement
    0.30
     biodegradation
    0.30
     vases
    0.30
     mineralization
    0.30
     cang
    0.30
    Activations Density 0.001%

    No Known Activations