© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7593
    Prev
    Next
    INDEX
    Explanations

    action completed by

    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
    ไปด้วย
    0.96
     reacts
    0.95
     pake
    0.91
     behaves
    0.88
     pacc
    0.85
     dotato
    0.84
    낌
    0.83
     nyeri
    0.83
     passwd
    0.83
     detects
    0.82
    POSITIVE LOGITS
    년대
    0.78
    ーム
    0.72
    ו
    0.71
     Ent
    0.70
     Rod
    0.69
    SizePolicy
    0.69
    خل
    0.68
     बचें
    0.68
    esco
    0.67
     рас
    0.67
    Activations Density 0.066%

    No Known Activations