© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 14030
    Prev
    Next
    INDEX
    Explanations

    evening followed by colon

    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
    i
    1.97
    ழ்ப
    1.89
    중
    1.82
    We
    1.81
    y
    1.80
    ਵੀ
    1.78
    πως
    1.76
    we
    1.69
     else
    1.69
     simply
    1.68
    POSITIVE LOGITS
     لگ
    2.69
     QnrB
    2.57
    hatiti
    2.52
    닝
    2.42
     വൃ
    2.42
    रखाव
    2.39
     Maraton
    2.38
     modelBuilder
    2.38
     troughs
    2.37
     CustB
    2.37
    Activations Density 0.073%

    No Known Activations