© 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. 439
    Prev
    Next
    INDEX
    Explanations

    to + action verb

    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
    ’
    0.80
    s
    0.79
    nis
    0.72
    /
    0.70
    (
    0.69
    的
    0.68
    )
    0.67
    '
    0.67
     /
    0.64
    ↵↵
    0.62
    POSITIVE LOGITS
     signify
    1.10
     supaya
    1.07
    Чтобы
    1.05
     waardoor
    1.02
    <unused954>
    1.02
     ensure
    1.01
    เพื่อให้
    0.99
    glightbox
    0.98
     اجازه
    0.97
    mathspace
    0.97
    Activations Density 1.165%

    No Known Activations