© 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. 4142
    Prev
    Next
    INDEX
    Explanations

    partial derivatives

    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
    Negative Logits
     P
    1.74
     K
    1.59
     Horse
    1.49
     Jan
    1.48
     N
    1.48
     S
    1.47
     Southern
    1.44
     Qu
    1.44
     raided
    1.44
     Ch
    1.39
    POSITIVE LOGITS
    ExpNow
    2.09
     izinsuku
    2.02
     UICtrl
    1.94
     ivvu
    1.93
     dissati
    1.92
    <unused1176>
    1.91
    pO
    1.90
    νε
    1.88
    wpilibj
    1.87
    ㄺ
    1.85
    Activations Density 0.115%

    No Known Activations