© 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. 10369
    Prev
    Next
    INDEX
    Explanations

    programming punctuation preceding comments

    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
     par
    0.88
     Par
    0.83
     な
    0.76
     おしゃれ
    0.75
     someone
    0.75
     Tar
    0.70
     \[
    0.70
     Na
    0.69
     Ве
    0.67
     Ха
    0.67
    POSITIVE LOGITS
     আহম্মদ
    0.95
    íticos
    0.93
    uerdo
    0.91
    իտ
    0.90
    ündung
    0.89
    publique
    0.87
    ainkan
    0.87
    clamation
    0.87
    kennung
    0.86
    Kemudian
    0.86
    Activations Density 0.218%

    No Known Activations