© 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. 13-GEMMASCOPE-2-RES-16K
    7. 12358
    Prev
    Next
    INDEX
    Explanations

    conjunctions and connectors

    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_13_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
     piecewise
    0.86
    <unused1935>
    0.85
    <unused1672>
    0.85
    Ⴊ
    0.84
    刋
    0.83
     hikers
    0.83
     "????.??.??"]
    0.83
    <unused446>
    0.82
    mall
    0.82
     കമ്മി
    0.82
    POSITIVE LOGITS
     и
    0.73
    และ
    0.72
    ↵
    0.69
    ↵↵
    0.69
     and
    0.68
    และความ
    0.65
    及び
    0.64
    そして
    0.64
     và
    0.63
    នូវ
    0.63
    Activations Density 14.840%

    No Known Activations