© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14373
    Prev
    Next
    INDEX
    Explanations

    avoiding eye contact

    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
    𝑟
    1.83
    𝑠
    1.81
    FindFileData
    1.80
    AnalyzeAction
    1.74
    𝑙
    1.73
    റിച്ച്
    1.69
    UseVisualStyle
    1.69
    roductive
    1.69
    ায়ী
    1.67
    𝑥
    1.67
    POSITIVE LOGITS
    算了
    1.44
    Cheap
    1.40
    ্ধ্য
    1.25
    í
    1.23
    Ui
    1.23
     lẽ
    1.22
    요일
    1.19
     Cheap
    1.16
    ts
    1.15
    Ặ
    1.15
    Activations Density 0.120%

    No Known Activations