© 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. 40-GEMMASCOPE-2-RES-262K
    7. 6089
    Prev
    Next
    INDEX
    Explanations

    pills, supplements, creams

    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_40_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
    硖
    0.35
    穸
    0.35
     arbets
    0.35
    缛
    0.35
    銠
    0.34
    ništva
    0.33
     фотоап
    0.33
    蒎
    0.33
     عمان
    0.32
     pch
    0.32
    POSITIVE LOGITS
     medications
    0.49
     medication
    0.41
     Medications
    0.41
     herbal
    0.40
     pills
    0.37
     Herbal
    0.37
     medicines
    0.37
     supplements
    0.35
     Ayurvedic
    0.33
    <0xE2>
    0.33
    Activations Density 0.000%

    No Known Activations