© 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. 13200
    Prev
    Next
    INDEX
    Explanations

    what questions

    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
     pursuant
    1.03
     member
    1.02
     folgender
    1.01
     Member
    0.97
     하게
    0.94
     Pursuant
    0.91
     Macintosh
    0.91
    該
    0.90
     Aboriginal
    0.89
     Ot
    0.88
    POSITIVE LOGITS
     değil
    1.34
     molécules
    1.33
    não
    1.33
     anzi
    1.32
     ведь
    1.30
    就像
    1.30
    hence
    1.29
     chứ
    1.26
     pétales
    1.25
     więc
    1.24
    Activations Density 0.388%

    No Known Activations