© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11085
    Prev
    Next
    INDEX
    Explanations

    addressing problems and offering solutions

    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
     определя
    1.00
     poised
    0.98
     aucune
    0.95
     précédemment
    0.95
     (:
    0.94
     alcuna
    0.91
     אמ
    0.90
    assan
    0.90
     કે
    0.89
    лната
    0.88
    POSITIVE LOGITS
     получилось
    1.03
    忙
    1.01
     pintura
    0.99
    他们的
    0.97
     তারাও
    0.95
     greenhouses
    0.94
     they
    0.94
     birdies
    0.93
     polytopes
    0.93
    麻烦
    0.92
    Activations Density 0.169%

    No Known Activations