© 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. 13432
    Prev
    Next
    INDEX
    Explanations

    don't ambush

    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
    cope
    1.28
    ョ
    1.26
    off
    1.25
     Bere
    1.20
    aff
    1.19
     sections
    1.17
     Section
    1.15
     tabs
    1.14
    after
    1.13
     Sections
    1.13
    POSITIVE LOGITS
    𝘥
    2.24
    
    1.82
    𝐝
    1.79
     wyjątk
    1.77
    𝘣
    1.75
    ם
    1.72
    
    1.72
    ⚊
    1.71
    steuerung
    1.71
     sentença
    1.70
    Activations Density 0.034%

    No Known Activations