© 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. 16-GEMMASCOPE-2-RES-262K
    7. 20775
    Prev
    Next
    INDEX
    Explanations

    constructor and initialization

    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_16_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
     payments
    0.60
    T
    0.60
     locust
    0.58
    ಕಿ
    0.57
     authorise
    0.55
    н
    0.55
     бонусы
    0.54
     visualise
    0.54
     দিবস
    0.54
    ুহ
    0.54
    POSITIVE LOGITS
    য়াদ
    0.59
    मैं
    0.55
    claimer
    0.54
    ，
    0.53
     với
    0.52
    Wooden
    0.52
    dengan
    0.52
                          
    0.51
    initialize
    0.50
     וב
    0.50
    Activations Density 0.068%

    No Known Activations