© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13587
    Prev
    Next
    INDEX
    Explanations

    phone numbers with 422 or 426

    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
     admon
    1.55
     vertices
    1.54
     синх
    1.50
    sType
    1.50
    ଧ
    1.48
     encounter
    1.48
     encounters
    1.46
    ющими
    1.46
    лександ
    1.43
    澗
    1.43
    POSITIVE LOGITS
     nowego
    1.45
     vorgestellt
    1.44
    ্ধ্য
    1.26
    一款
    1.24
    adığı
    1.22
     rak
    1.21
     জাত
    1.21
     gyerek
    1.17
     nedost
    1.17
     bang
    1.16
    Activations Density 0.131%

    No Known Activations