© 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. 606
    Prev
    Next
    INDEX
    Explanations

    ending or stopping actions

    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
    ンジ
    1.68
    𝘀
    1.66
    槿
    1.62
    ꯔ
    1.59
    σε
    1.59
    齊
    1.54
     Merrick
    1.54
    ็ว
    1.53
     চাল
    1.53
    मंगल
    1.52
    POSITIVE LOGITS
    掉
    1.73
    此之外
    1.45
     altogether
    1.30
    াদির
    1.30
     cessation
    1.28
     retirer
    1.23
    掉了
    1.22
     оставить
    1.19
    unsubscribe
    1.19
    ————
    1.19
    Activations Density 2.143%

    No Known Activations