© 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. 14369
    Prev
    Next
    INDEX
    Explanations

    web URLs with uploads

    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
     det
    0.37
     somew
    0.36
     solemnly
    0.35
    𝑂
    0.34
     potente
    0.33
     piece
    0.33
     Hollow
    0.33
     pouvez
    0.33
    ሼ
    0.33
     détaillé
    0.33
    POSITIVE LOGITS
    uploads
    0.73
     uploads
    0.62
    cache
    0.48
     Upload
    0.47
    scrollHeight
    0.47
    Uploaded
    0.46
    plugins
    0.46
     сай
    0.45
    WordPress
    0.45
    sites
    0.43
    Activations Density 0.001%

    No Known Activations