© 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. 2074
    Prev
    Next
    INDEX
    Explanations

    forgotten history, civilization, memories

    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
    .
    1.44
    ,
    1.40
     are
    1.36
     is
    1.34
     on
    1.30
     from
    1.27
     with
    1.26
     have
    1.25
     a
    1.24
     to
    1.22
    POSITIVE LOGITS
     kebijakan
    2.06
     pengelolaan
    1.97
     Pengembangan
    1.95
     laporan
    1.95
     kegiatan
    1.94
    梅里尼亚克
    1.93
     keuntungan
    1.92
     pengembangan
    1.92
     kemampuan
    1.92
     strListName
    1.92
    Activations Density 0.014%

    No Known Activations