© 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. 3886
    Prev
    Next
    INDEX
    Explanations

    fragmented memories

    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
    obatan
    2.70
    驒
    2.53
    opia
    2.35
    Okay
    2.25
    ecture
    2.25
    osis
    2.21
    ซ์
    2.21
    खार
    2.17
    crollView
    2.17
    require
    2.13
    POSITIVE LOGITS
    DrawerToggle
    3.26
    hua
    2.91
    दारों
    2.69
    ｆ
    2.67
    ହା
    2.64
    玩意
    2.54
    oor
    2.49
    Ո
    2.47
    hko
    2.46
    ⌔
    2.44
    Activations Density 0.082%

    No Known Activations