© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74770
    Prev
    Next
    INDEX
    Explanations

    as seen in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    埼
    -1.52
    ácii
    -1.52
    ton
    -1.51
     soms
    -1.47
    してみた
    -1.45
    ”
    -1.44
    imetry
    -1.41
     expérience
    -1.41
    x
    -1.40
    WidgetItem
    -1.39
    POSITIVE LOGITS
     jepang
    1.55
     Lainnya
    1.41
     reluctance
    1.34
    برج
    1.33
    ühnen
    1.32
     loath
    1.31
    加拿
    1.29
    abbix
    1.29
     terminó
    1.27
    Ostat
    1.27
    Activations Density 0.045%

    No Known Activations