© 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. 14666
    Prev
    Next
    INDEX
    Explanations

    buy one get one

    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
     Правда
    1.50
    しかも
    1.47
     staffers
    1.41
    而且
    1.32
    '],'
    1.31
     hatta
    1.30
    なかった
    1.30
    ')[
    1.29
     bahkan
    1.29
    それでも
    1.27
    POSITIVE LOGITS
    aktadır
    1.28
    ini
    1.26
    inar
    1.24
    izi
    1.22
    ศาสตร์
    1.22
    ille
    1.22
    äd
    1.22
    ensis
    1.21
    izo
    1.18
    께서
    1.17
    Activations Density 0.060%

    No Known Activations