© 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. 13-GEMMASCOPE-2-RES-65K
    7. 2190
    Prev
    Next
    INDEX
    Explanations

    new and emerging concepts

    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_13_width_65k_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
    ্থ
    1.33
    !/"
    1.33
    pred
    1.25
    RECT
    1.23
    Cum
    1.21
     Struggle
    1.17
    wood
    1.17
    中的
    1.17
    HON
    1.17
    ैम
    1.17
    POSITIVE LOGITS
     arrivé
    1.93
    ◸
    1.78
    𝓱
    1.74
    𝒾
    1.73
    topia
    1.64
    تری
    1.62
    𝖑
    1.62
    ඪ
    1.61
    𝒶
    1.58
    িদ্ধ
    1.58
    Activations Density 0.248%

    No Known Activations