© 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. 13229
    Prev
    Next
    INDEX
    Explanations

    special characters and repetitive sequences

    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
    žel
    2.64
    selen
    2.47
    sb
    2.43
    ówn
    2.37
    싣
    2.32
    menin
    2.28
     sebaik
    2.26
    munder
    2.25
    বাত
    2.25
    kannya
    2.23
    POSITIVE LOGITS
    ed
    2.87
    urence
    2.73
     isTestSource
    2.53
    Ed
    2.48
    ED
    2.33
    র্ধ্ব
    2.26
    ants
    2.24
    た
    2.23
    禁
    2.22
    &=\
    2.21
    Activations Density 0.004%

    No Known Activations