© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 16362
    Prev
    Next
    INDEX
    Explanations

    defining custom structures or shortcuts

    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
    AddComponent
    0.43
     spawned
    0.40
    classname
    0.40
    anii
    0.39
    يّ
    0.39
     satunya
    0.39
     Both
    0.38
    析
    0.38
     culminated
    0.38
     both
    0.37
    POSITIVE LOGITS
     macros
    0.80
     shortcuts
    0.74
     aliases
    0.73
     Macros
    0.73
     definitions
    0.72
     custom
    0.67
     Shortcuts
    0.67
    Definitions
    0.66
    Macros
    0.64
     shortcut
    0.64
    Activations Density 0.003%

    No Known Activations