© 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. 1294
    Prev
    Next
    INDEX
    Explanations

    win, Windows, wings

    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
    𝗼
    3.24
    VCTargetsPath
    3.11
    xadmin
    2.92
    ">⁡</
    2.91
    𝓷
    2.85
    सोल
    2.83
     primarySwatch
    2.80
    𝘆
    2.73
     scab
    2.71
    𝗿
    2.71
    POSITIVE LOGITS
    ة
    2.88
    kaan
    2.82
    moveTo
    2.52
    ki
    2.40
    ku
    2.39
    ្រី
    2.36
    ্স
    2.30
    からない
    2.26
    strahlung
    2.26
    د
    2.24
    Activations Density 0.962%

    No Known Activations