© 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. 10182
    Prev
    Next
    INDEX
    Explanations

    requests and foreign words

    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
    瘙
    0.66
     clumps
    0.66
    neighbor
    0.64
     neighbourhoods
    0.61
    neighbour
    0.61
    flowing
    0.60
     поступа
    0.60
     flowing
    0.59
    πη
    0.59
     transpiration
    0.58
    POSITIVE LOGITS
    烣
    0.70
     uniquement
    0.66
    েশন
    0.65
    گنڈ
    0.62
    美國
    0.62
    台灣
    0.61
     Bahasa
    0.60
     Amerikan
    0.60
    詼
    0.60
     如何
    0.60
    Activations Density 0.330%

    No Known Activations