© 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-65K
    7. 1785
    Prev
    Next
    INDEX
    Explanations

    date, hotel, passions

    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_65k_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
    рати
    1.70
    RVCT
    1.65
    芈
    1.64
    嘖
    1.62
     později
    1.61
     NIS
    1.60
    getMove
    1.60
    probable
    1.56
    eventName
    1.53
     satisfactory
    1.51
    POSITIVE LOGITS
    ardt
    1.42
    ๋ยว
    1.31
    循
    1.31
    ہ
    1.29
    igheden
    1.25
    𝘀
    1.24
    框
    1.22
     tragedies
    1.22
    ຖານ
    1.20
     Chương
    1.20
    Activations Density 0.000%

    No Known Activations