© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 142
    Prev
    Next
    INDEX
    Explanations

    sentence completion patterns

    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_7_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
    ر
    1.68
    er
    1.50
    ി
    1.45
    elik
    1.42
    н
    1.39
    र
    1.32
    staking
    1.25
    liness
    1.24
    ার
    1.21
    ៉
    1.21
    POSITIVE LOGITS
    अय
    1.29
    ून्य
    1.27
    zaXR
    1.23
    ल्पनिक
    1.21
    佥
    1.21
     Figuren
    1.18
     terd
    1.17
     strony
    1.16
     sprawy
    1.16
    CharArray
    1.15
    Activations Density 0.002%

    No Known Activations