© 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. 5523
    Prev
    Next
    INDEX
    Explanations

    comma-separated lists or output format

    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
    ेष
    0.93
    窩
    0.87
     local
    0.87
    掛
    0.87
     joe
    0.87
     Liza
    0.85
     Angelo
    0.82
     Andy
    0.82
     Ricky
    0.81
     Reinhold
    0.81
    POSITIVE LOGITS
     pretrained
    0.99
    utacji
    0.99
    leding
    0.99
    빴
    0.96
     Онлайн
    0.93
     proposés
    0.93
     proposent
    0.93
    👇
    0.93
    ępuje
    0.92
    👻
    0.91
    Activations Density 2.655%

    No Known Activations