© 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. 1293
    Prev
    Next
    INDEX
    Explanations

    and the, and you, and for

    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
    -
    1.69
    etah
    1.53
    chea
    1.44
    :
    1.44
    visional
    1.43
    cl
    1.43
    idential
    1.41
    н
    1.41
    obox
    1.38
     (?
    1.38
    POSITIVE LOGITS
     hatta
    2.48
    这也
    2.47
    それが
    2.42
     durchaus
    2.32
     이는
    2.28
     tämä
    2.25
    これが
    2.25
     consequently
    2.24
    ंगाबाद
    2.16
     oftentimes
    2.14
    Activations Density 1.432%

    No Known Activations