© 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. 7-GEMMASCOPE-2-RES-16K
    7. 1213
    Prev
    Next
    INDEX
    Explanations

    supplements

    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_7_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
    개의
    1.80
    었던
    1.50
     الدكتور
    1.46
    da
    1.46
     ahli
    1.46
     lulus
    1.45
    त्रेयी
    1.41
    숴
    1.40
     Trouble
    1.38
     muka
    1.38
    POSITIVE LOGITS
     compels
    1.73
    ую
    1.71
    ్వ
    1.70
     ingrained
    1.64
    ometimes
    1.62
     varies
    1.54
     resembles
    1.53
    causing
    1.50
     undermines
    1.48
     eroding
    1.48
    Activations Density 0.348%

    No Known Activations