Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12827
    Prev
    Next
    INDEX
    Explanations

    c++ public class definitions

    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_16k_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
     কাউন্সিল
    0.40
    т
    0.40
     pleasant
    0.39
    Markdown
    0.38
    ग
    0.38
    د
    0.38
    Г
    0.38
     supported
    0.37
     Markdown
    0.37
    л
    0.37
    POSITIVE LOGITS
    calup
    0.45
    PatientR
    0.43
     меха
    0.42
     අධ
    0.40
    ность
    0.39
    RatingDiff
    0.39
     کم
    0.39
     trud
    0.39
    य्
    0.38
    вав
    0.38
    Activations Density 0.054%

    No Known Activations