© 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-65K
    7. 995
    Prev
    Next
    INDEX
    Explanations

    what type or kind

    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_65k_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
    (
    1.02
     (
    0.92
    -(
    0.85
    ctu
    0.79
     (“
    0.77
    ..(
    0.77
    (“
    0.75
     out
    0.74
    -
    0.72
     («
    0.71
    POSITIVE LOGITS
     melakukan
    1.86
     berbagai
    1.77
     mahasiswa
    1.71
     hubungan
    1.67
     kegiatan
    1.66
     Pendidikan
    1.65
     pembelajaran
    1.64
     komunikasi
    1.62
     verschiedene
    1.62
    endidikan
    1.62
    Activations Density 0.066%

    No Known Activations