© 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. 2832
    Prev
    Next
    INDEX
    Explanations

    switch between

    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
    s
    1.60
    spl
    1.49
    いる
    1.46
    t
    1.33
    いた
    1.30
    σω
    1.29
    sie
    1.28
    r
    1.28
    いて
    1.27
    تش
    1.25
    POSITIVE LOGITS
     แห่ง
    1.80
     fontstyle
    1.80
    溼
    1.64
    ര്‍ഷ
    1.61
     usados
    1.61
    aní
    1.59
     ideales
    1.59
     IActionResult
    1.58
     Autón
    1.58
    áctica
    1.57
    Activations Density 0.105%

    No Known Activations