© 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-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 14592
    Prev
    Next
    INDEX
    Explanations

    wet ingredients or descriptive terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    an
    2.74
    adou
    2.37
    ad
    2.16
    u
    2.13
    Around
    2.03
     ad
    2.02
    ascending
    1.96
    ি
    1.96
    S
    1.92
    anet
    1.90
    POSITIVE LOGITS
    らっしゃ
    3.03
    ங்கிணை
    3.03
    TreeWidgetItem
    3.02
    㡀
    2.76
    فيذ
    2.69
    ypeł
    2.69
    り
    2.66
    folded
    2.64
    াবেক
    2.62
    ătate
    2.61
    Activations Density 0.012%

    No Known Activations