© 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. 1090
    Prev
    Next
    INDEX
    Explanations

    equality checks

    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
    －
    0.95
    消
    0.94
    給
    0.93
    ｰ
    0.92
    葉
    0.90
    <unused1959>
    0.90
    －－
    0.89
    雷
    0.88
    <start_of_image>
    0.88
     ευ
    0.88
    POSITIVE LOGITS
     adenine
    2.32
     ampere
    2.31
     welche
    2.04
     unseren
    1.90
     unsere
    1.90
     diese
    1.86
     aforementioned
    1.85
     dieser
    1.84
     meine
    1.84
     einige
    1.81
    Activations Density 0.166%

    No Known Activations