© 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. 12881
    Prev
    Next
    INDEX
    Explanations

    benign tumors and growths

    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
     систему
    0.49
    ogram
    0.46
    丧
    0.46
     потери
    0.46
    Severe
    0.45
     потеря
    0.44
     severely
    0.43
    เป็นการ
    0.43
    г
    0.43
    郯
    0.43
    POSITIVE LOGITS
     benign
    0.71
     tumors
    0.67
     growths
    0.65
     growth
    0.60
     harmless
    0.57
     tumorigen
    0.56
     blobs
    0.54
     blob
    0.54
     cancerous
    0.53
     innocuous
    0.53
    Activations Density 0.045%

    No Known Activations