© 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. 537
    Prev
    Next
    INDEX
    Explanations

    specific item or instance

    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
    <0xF3>
    2.74
     untuk
    2.50
     và
    2.50
    และ
    2.44
    It
    2.37
     has
    2.35
     এবং
    2.35
     It
    2.35
     и
    2.35
     is
    2.34
    POSITIVE LOGITS
     latter
    1.76
     myriad
    1.64
     socalled
    1.57
    പക്ഷ
    1.53
    egir
    1.52
     hypothetical
    1.51
     multitude
    1.50
     afore
    1.48
     sizeable
    1.47
     aforementioned
    1.46
    Activations Density 1.378%

    No Known Activations