© 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. 3940
    Prev
    Next
    INDEX
    Explanations

    C++ output statements

    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
    Negative Logits
    t
    1.37
    equal
    1.33
    s
    1.30
     under
    1.24
     equal
    1.22
    e
    1.17
    Equal
    1.13
    ur
    1.13
    Under
    1.12
    ↵
    1.11
    POSITIVE LOGITS
    <unused1952>
    2.62
    쮿
    2.56
    <unused344>
    2.43
    <unused1903>
    2.42
    <unused1177>
    2.40
    <unused1193>
    2.40
    <unused431>
    2.39
    
    2.37
     titleImageUrl
    2.37
    귋
    2.36
    Activations Density 0.057%

    No Known Activations