© 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. 13-GEMMASCOPE-2-RES-16K
    7. 13078
    Prev
    Next
    INDEX
    Explanations

    storage device, networking hardware, GPT

    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_13_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
    and
    1.09
     счета
    1.01
    ,
    0.99
    ri
    0.98
    sound
    0.97
    with
    0.95
    tho
    0.94
    without
    0.94
     небо
    0.94
     without
    0.92
    POSITIVE LOGITS
     meminta
    1.65
     bentuk
    1.52
     Đặc
    1.48
     mengubah
    1.46
     *)$
    1.45
     Änderungen
    1.44
    Centers
    1.43
     Centers
    1.43
     Sử
    1.43
    GetComponents
    1.42
    Activations Density 0.000%

    No Known Activations