© 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. 13-GEMMASCOPE-2-RES-16K
    7. 10888
    Prev
    Next
    INDEX
    Explanations

    definitions and specific terms

    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
     decently
    1.24
     downwards
    1.18
    reduction
    1.15
     ぐらい
    1.14
     ActiveRecord
    1.13
     reduction
    1.13
    降低
    1.12
     (\<
    1.12
    %/
    1.11
     painless
    1.11
    POSITIVE LOGITS
    Official
    1.18
     Oficial
    1.07
     Cla
    1.05
    ગો
    1.03
    গল
    1.01
     Official
    1.01
     ufficiale
    1.01
     Polo
    0.98
     Confusion
    0.98
    ت
    0.97
    Activations Density 0.000%

    No Known Activations