© 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. 1508
    Prev
    Next
    INDEX
    Explanations

    Pixel, DOCTYPE, Power

    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
     إلى
    1.68
     및
    1.53
     وم
    1.52
    2
    1.50
    6
    1.46
    The
    1.46
     ومن
    1.44
    Identify
    1.44
    7
    1.44
    4
    1.43
    POSITIVE LOGITS
     insanlar
    1.71
     plupart
    1.58
    里面
    1.58
     shitty
    1.57
    jenigen
    1.52
     crappy
    1.50
     meeste
    1.50
     kiddos
    1.50
     shit
    1.49
     galera
    1.49
    Activations Density 0.753%

    No Known Activations