© 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. 11814
    Prev
    Next
    INDEX
    Explanations

    algorithmic complexity O(n log n)

    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
    MUSIC
    2.85
    ======
    2.58
    ᅱ
    2.57
    <!---
    2.57
     clippings
    2.50
    
    2.48
    bboxes
    2.47
    𝓱
    2.40
    allocation
    2.39
    きました
    2.38
    POSITIVE LOGITS
    yı
    3.62
    enyl
    3.23
    genden
    3.22
    น
    3.07
    nements
    2.99
    ੀ
    2.99
    yay
    2.90
    dehyde
    2.90
    tj
    2.88
    de
    2.86
    Activations Density 0.012%

    No Known Activations