© 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. 13338
    Prev
    Next
    INDEX
    Explanations

    late afternoon

    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
    ly
    2.69
    s
    2.66
    다고
    2.29
    ン
    2.25
    spe
    2.23
    了
    2.21
    sst
    2.21
    sels
    2.19
    tp
    2.15
    ع
    2.11
    POSITIVE LOGITS
    خر
    2.36
    цвет
    2.33
    Suffix
    2.32
    falling
    2.26
    Falling
    2.26
     excused
    2.26
     prossima
    2.24
    ﻡ
    2.18
    早
    2.17
     “”
    2.12
    Activations Density 0.006%

    No Known Activations