© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10145
    Prev
    Next
    INDEX
    Explanations

    average counterparts in foreign languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_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
     than
    1.98
    Than
    1.79
     Than
    1.67
    than
    1.66
     niż
    1.45
     kuin
    1.37
     compared
    1.26
    比
    1.23
    compared
    1.21
     än
    1.20
    POSITIVE LOGITS
     counterparts
    0.94
     counterpart
    0.83
     averages
    0.78
     promedio
    0.78
     does
    0.77
     avrebbe
    0.77
    tem
    0.75
     ofrece
    0.75
     biedt
    0.74
     ofrecen
    0.73
    Activations Density 0.246%

    No Known Activations