© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14856
    Prev
    Next
    INDEX
    Explanations

    DOCTYPE html preamble

    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
    er
    3.21
    erar
    2.58
    ה
    2.58
    huis
    2.52
    होस्
    2.47
    emf
    2.31
    juč
    2.30
    erate
    2.22
     Selatan
    2.21
     segi
    2.21
    POSITIVE LOGITS
    了
    3.85
    nya
    3.68
    tttt
    3.58
    tter
    3.23
    sb
    3.12
    sd
    2.97
    ttt
    2.95
    นาน
    2.94
    tr
    2.94
    lift
    2.93
    Activations Density 0.010%

    No Known Activations