© 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-16K
    7. 1894
    Prev
    Next
    INDEX
    Explanations

    evaluative qualifiers

    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_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
    not
    2.68
    ly
    2.59
    nya
    2.54
    ের
    2.52
    क
    2.46
    nt
    2.46
    了
    2.44
    man
    2.43
    页面存档备份
    2.43
    犸
    2.41
    POSITIVE LOGITS
    Луч
    2.39
     الحره
    2.33
     पाण्डे
    2.28
    ἤ
    2.22
    Bild
    2.21
    컷
    2.19
    жей
    2.15
    شک
    2.15
    емого
    2.15
    Также
    2.12
    Activations Density 0.545%

    No Known Activations