© 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. 1282
    Prev
    Next
    INDEX
    Explanations

    acronyms and initials

    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
    Allora
    1.83
    Ano
    1.77
     kial
    1.74
    ቀር
    1.73
    ‪
    1.71
    Unable
    1.68
     पूछता
    1.68
    Talking
    1.65
    Estas
    1.64
    ّ
    1.62
    POSITIVE LOGITS
     美
    1.85
    <unused1059>
    1.79
     투
    1.78
    <unused418>
    1.73
    ＇
    1.72
    <unused969>
    1.72
     木
    1.71
    <unused2040>
    1.70
    <unused977>
    1.68
    <unused1171>
    1.67
    Activations Density 0.202%

    No Known Activations