© 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. 1330
    Prev
    Next
    INDEX
    Explanations

    foreign language characters

    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
    茣
    2.70
    ʀ
    2.60
    ्ञ
    2.56
    ћа
    2.54
     moſt
    2.49
    𝐫
    2.49
    Ced
    2.43
    ће
    2.42
    oC
    2.39
    𝐠
    2.34
    POSITIVE LOGITS
    ">(</
    2.61
    y
    2.38
    zonej
    2.34
    ximo
    2.16
    ΕΙ
    2.14
    ują
    2.13
     centrales
    2.13
    숑
    2.11
    lichkeit
    2.11
    μαστε
    2.11
    Activations Density 0.755%

    No Known Activations