© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6134
    Prev
    Next
    INDEX
    Explanations

    in a

    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
     هيا
    1.39
     المراجعه
    1.31
    StorageSync
    1.26
     đều
    1.25
     Vào
    1.25
     fueran
    1.25
    𒄿
    1.24
     andDevice
    1.23
     Bereiche
    1.21
     شوند
    1.20
    POSITIVE LOGITS
     which
    1.36
    which
    1.19
     cui
    1.15
     whose
    1.11
     जिसका
    0.99
     которое
    0.94
     of
    0.91
    2
    0.90
     that
    0.90
     wich
    0.89
    Activations Density 0.218%

    No Known Activations