© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10487
    Prev
    Next
    INDEX
    Explanations

    Douglas Adams

    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
    𝐠
    2.81
    ﮈ
    2.80
    ozems
    2.69
    𝐬
    2.51
     বদি
    2.43
    ুপ্ত
    2.35
    𝐛
    2.33
    
    2.32
    𝐝
    2.30
    isher
    2.30
    POSITIVE LOGITS
    ्यक्रम
    2.43
     ^^
    2.43
     ।
    2.37
    ^^
    2.37
     ，
    2.35
    wot
    2.28
    appeared
    2.28
     («
    2.23
     »
    2.22
    msqrt
    2.21
    Activations Density 0.032%

    No Known Activations