© 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. 13-GEMMASCOPE-2-RES-16K
    7. 14453
    Prev
    Next
    INDEX
    Explanations

    @echo off

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ំព
    0.97
     Cru
    0.96
     &:
    0.92
     называется
    0.92
    UMS
    0.91
    cru
    0.91
    bR
    0.90
     имеется
    0.89
     जुड़ी
    0.88
    :@
    0.88
    POSITIVE LOGITS
     upfront
    1.21
     zunächst
    1.19
     पौराणिक
    1.15
     initially
    1.14
     inicialmente
    1.14
     tahap
    1.13
     récemment
    1.12
     erste
    1.09
     first
    1.09
    初代
    1.09
    Activations Density 0.104%

    No Known Activations