© 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. 17737
    Prev
    Next
    INDEX
    Explanations

    programming keywords

    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
     ပ
    0.38
    粼
    0.38
     ආර
    0.37
    味わ
    0.37
    ப்பிர
    0.36
    ‹
    0.36
     জাহ
    0.36
    伒
    0.35
    ǿ
    0.35
    荇
    0.35
    POSITIVE LOGITS
     updates
    0.43
     cre
    0.41
    赋值
    0.40
    nextSend
    0.40
     reass
    0.39
     Updates
    0.38
    ador
    0.37
     assignments
    0.36
     initialize
    0.36
     updating
    0.36
    Activations Density 0.031%

    No Known Activations