© 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. 1741
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting

    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
    및
    1.77
    utilizzo
    1.72
     obtuvo
    1.68
    ượu
    1.68
    calcular
    1.66
     décoration
    1.65
    蒾
    1.63
     হুগলী
    1.61
    ꪽ
    1.61
     destacó
    1.61
    POSITIVE LOGITS
    e
    1.21
     thing
    1.17
     truth
    1.10
     reality
    1.06
     world
    1.06
     of
    1.03
     damn
    1.03
     happening
    1.00
     way
    0.98
     happened
    0.97
    Activations Density 0.000%

    No Known Activations