© 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-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2238
    Prev
    Next
    INDEX
    Explanations

    data types and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     وبي
    0.72
    מ
    0.69
    Technology
    0.68
    technology
    0.67
     Technology
    0.65
     agré
    0.65
    ♧
    0.65
    ال
    0.65
    Equ
    0.65
    clusions
    0.65
    POSITIVE LOGITS
    <unused602>
    0.93
    <unused474>
    0.90
    Things
    0.88
     halfCanvas
    0.88
    <unused957>
    0.87
    assanam
    0.86
    SizePolicy
    0.86
    <unused1640>
    0.85
    <unused1695>
    0.84
    迺
    0.84
    Activations Density 0.235%

    No Known Activations