© 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. 8127
    Prev
    Next
    INDEX
    Explanations

    saying yes or no

    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
    oler
    1.21
    ulat
    1.17
    olan
    1.08
    atov
    1.04
    olat
    1.02
    daar
    1.01
    mixing
    1.00
     }-\
    1.00
    countery
    0.99
    kag
    0.99
    POSITIVE LOGITS
     Retrieved
    1.43
    Additionally
    1.34
     Additionally
    1.33
     Healthy
    1.32
     Approximately
    1.30
     HEALTH
    1.29
    Approximately
    1.29
    Webhook
    1.28
     dwRes
    1.28
    Healthy
    1.24
    Activations Density 0.061%

    No Known Activations