© 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-16K
    7. 1893
    Prev
    Next
    INDEX
    Explanations

    words followed by punctuation

    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
     雷
    1.32
    λιο
    1.29
     普通
    1.26
     않을
    1.24
    雷
    1.21
     mainframe
    1.20
    Ⓒ
    1.18
     accél
    1.18
    乑
    1.17
     expedite
    1.17
    POSITIVE LOGITS
     наличи
    0.93
    เขา
    0.88
     качества
    0.83
     elytra
    0.82
    Attributes
    0.82
    Both
    0.81
    素质
    0.77
    Alcohol
    0.77
    ข้าว
    0.77
    คุณภาพ
    0.77
    Activations Density 0.075%

    No Known Activations