© 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. 1528
    Prev
    Next
    INDEX
    Explanations

    end words: before, with, deadline, this

    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
     A
    1.87
    <em>
    1.85
     roots
    1.84
     simple
    1.81
    v
    1.77
     freely
    1.75
     news
    1.73
    uximab
    1.73
     ug
    1.72
     radical
    1.71
    POSITIVE LOGITS
    ExpNow
    3.01
    gült
    2.55
     фай
    2.51
     resolvers
    2.50
     концов
    2.47
    ក្រោយ
    2.44
    termination
    2.36
    帧
    2.35
     وظ
    2.33
    ?\\
    2.33
    Activations Density 0.748%

    No Known Activations