© 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. 2797
    Prev
    Next
    INDEX
    Explanations

    network latency, settings, traffic, policies

    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
    boro
    1.98
    c
    1.97
    to
    1.82
    타고
    1.57
    ted
    1.56
     {"
    1.56
    In
    1.54
    וט
    1.54
    cent
    1.53
    gro
    1.53
    POSITIVE LOGITS
    峻
    2.29
    ന്തപു
    2.20
    橥
    2.17
    uido
    2.16
    arrêt
    2.14
    𝑠
    2.12
     complicado
    2.11
     transcriptome
    2.11
    applicazione
    2.11
     প্রতিবেদ
    2.11
    Activations Density 0.003%

    No Known Activations