© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 15171
    Prev
    Next
    INDEX
    Explanations

    xaml or svg namespaces

    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_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
     thermally
    0.91
     |.
    0.85
     palma
    0.84
     grammatical
    0.83
     aider
    0.83
     acho
    0.81
    鈷
    0.81
    ロ
    0.79
     नाही
    0.78
     inconsider
    0.76
    POSITIVE LOGITS
    "
    0.80
    Стра
    0.75
    тиву
    0.73
    caya
    0.72
    ުގެ
    0.71
    constraint
    0.70
     SLS
    0.70
    ogli
    0.70
    Spring
    0.69
    错
    0.68
    Activations Density 0.000%

    No Known Activations