© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9849
    Prev
    Next
    INDEX
    Explanations

    loss calculation and types

    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
     collars
    0.92
    昕
    0.88
     colonies
    0.87
     জাত
    0.83
     collar
    0.83
     PLANTS
    0.83
     plantilla
    0.83
     নির্বাচনের
    0.82
    펭
    0.81
     Colonies
    0.81
    POSITIVE LOGITS
    NORM
    1.15
     Minim
    1.14
    Loss
    1.13
     $\|\
    1.11
    刑
    1.10
    (||
    1.09
     minimization
    1.09
     $\|
    1.07
    criterion
    1.07
    norms
    1.05
    Activations Density 0.083%

    No Known Activations