© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10794
    Prev
    Next
    INDEX
    Explanations

    every day

    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
    ه
    3.17
    ی
    3.09
    া
    3.01
     spind
    2.91
    a
    2.80
    aş
    2.79
    ipay
    2.75
    i
    2.74
    ڈر
    2.61
    o
    2.57
    POSITIVE LOGITS
    лук
    3.20
    胛
    2.65
     [&](
    2.57
    ComponentModel
    2.57
    Послед
    2.53
    Ỷ
    2.52
    giờ
    2.52
    מה
    2.51
    BREAK
    2.50
    قت
    2.48
    Activations Density 0.003%

    No Known Activations