© 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. 20698
    Prev
    Next
    INDEX
    Explanations

    performance comparison

    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
    ಗೋ
    0.37
    घ्र
    0.36
    助
    0.34
     Ideal
    0.34
     Patience
    0.33
    顾
    0.33
    ree
    0.33
    ---------------
    0.33
     ब्लॉक
    0.33
     udal
    0.33
    POSITIVE LOGITS
     comparable
    1.89
     equal
    1.62
     Comparable
    1.50
    媲
    1.47
     igual
    1.42
     equivalent
    1.41
     equaling
    1.41
    Comparable
    1.39
     rival
    1.38
    equal
    1.38
    Activations Density 0.033%

    No Known Activations