© 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. 3931
    Prev
    Next
    INDEX
    Explanations

    Kaggle datasets and learning

    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
    驒
    2.95
    岖
    2.81
    𝑙
    2.60
    𝑒
    2.52
    ్యా
    2.49
    ℎ
    2.49
    𝑢
    2.48
     žal
    2.44
    騨
    2.42
    avantage
    2.38
    POSITIVE LOGITS
    "।
    3.42
    memberNameLink
    2.82
    ποι
    2.34
    Ւ
    2.31
    ட
    2.30
    ."
    2.30
    ".
    2.29
    Й
    2.25
     dizi
    2.23
    кто
    2.18
    Activations Density 0.002%

    No Known Activations