© 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. 13-GEMMASCOPE-2-RES-16K
    7. 8508
    Prev
    Next
    INDEX
    Explanations

    checking Superset

    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
     dishonest
    1.72
     benefactor
    1.67
     congenital
    1.63
    ﾎ
    1.59
    ৱ
    1.57
     pituitary
    1.53
    ｳ
    1.53
     Housewives
    1.53
    wala
    1.51
     sinful
    1.51
    POSITIVE LOGITS
    으로
    1.32
     بالف
    1.31
     집중
    1.30
    氛
    1.29
     분위
    1.28
    skou
    1.28
     issu
    1.22
     breathe
    1.21
     Π
    1.16
    די
    1.16
    Activations Density 0.000%

    No Known Activations