© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9046
    Prev
    Next
    INDEX
    Explanations

    one-time

    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_22_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
    łe
    1.01
    projectlombok
    1.01
    enderung
    1.01
    attet
    1.00
    ുമ്പോൾ
    0.99
    !("{:
    0.97
    endem
    0.96
    čenje
    0.95
     Maas
    0.95
     owls
    0.95
    POSITIVE LOGITS
     Dispon
    0.91
     即
    0.90
     late
    0.89
     送料無料
    0.87
    争
    0.86
    <td>
    0.83
     เรียก
    0.80
     подготов
    0.80
    ার
    0.79
     開
    0.78
    Activations Density 0.007%

    No Known Activations