© 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. 2591
    Prev
    Next
    INDEX
    Explanations

    tables, divisions, and summing

    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
    wife
    0.92
     yen
    0.92
    ­
    0.91
    なのですが
    0.89
    ()-
    0.89
    /(
    0.89
    (?)
    0.88
     selle
    0.88
    ‐
    0.86
    –
    0.86
    POSITIVE LOGITS
    yrıca
    1.46
     cấu
    1.44
    ）.
    1.42
     注意
    1.42
     Außerdem
    1.41
     guter
    1.40
     význam
    1.40
    此外
    1.39
    ánh
    1.38
     Đặc
    1.38
    Activations Density 0.192%

    No Known Activations