© 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. 1377
    Prev
    Next
    INDEX
    Explanations

    numbers and dimensions

    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
     muito
    1.33
     biens
    1.32
     molto
    1.28
     clientes
    1.17
     dentro
    1.17
     не
    1.15
     exatamente
    1.14
     a
    1.12
     credito
    1.12
     dont
    1.11
    POSITIVE LOGITS
     largest
    1.27
    atrical
    1.25
     inaugural
    1.25
    largest
    1.23
     번째
    1.19
     coveted
    1.15
    ocratic
    1.14
     dreaded
    1.11
     latter
    1.10
     fifth
    1.10
    Activations Density 0.882%

    No Known Activations