© 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. 31-GEMMASCOPE-2-RES-65K
    7. 36886
    Prev
    Next
    INDEX
    Explanations

    international scripts and financial terms

    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_31_width_65k_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
     doubled
    0.47
     ন
    0.45
    Double
    0.43
     rencontrer
    0.43
    バー
    0.43
    CONTENTS
    0.43
     doubles
    0.43
    }+...
    0.43
     meets
    0.42
     izd
    0.42
    POSITIVE LOGITS
     เว
    0.46
    喲
    0.46
    ifting
    0.44
     Receivable
    0.44
     ومع
    0.43
     અનુસાર
    0.43
    으로서
    0.42
     প্রভৃতির
    0.42
    曌
    0.42
    μου
    0.42
    Activations Density 0.004%

    No Known Activations