© 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-262K
    7. 17646
    Prev
    Next
    INDEX
    Explanations

    cancer and chemotherapy

    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_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
     आविष्कार
    0.44
    定律
    0.41
    태
    0.41
    🧈
    0.40
    昅
    0.40
     нача
    0.40
    клары
    0.39
     俺
    0.39
    ຫຼາຍ
    0.39
    초
    0.38
    POSITIVE LOGITS
     oncologist
    0.90
     chemotherapy
    0.89
     oncology
    0.86
     cancer
    0.86
     anticancer
    0.85
     onc
    0.82
    Cancer
    0.80
    cancer
    0.80
     kanker
    0.77
     Oncology
    0.76
    Activations Density 0.036%

    No Known Activations