© 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. 13-GEMMASCOPE-2-RES-16K
    7. 527
    Prev
    Next
    INDEX
    Explanations

    mixed language phrases

    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
    S
    0.81
    e
    0.80
     ,
    0.80
     s
    0.76
     i
    0.75
    В
    0.73
     ect
    0.72
     even
    0.71
     te
    0.71
    A
    0.70
    POSITIVE LOGITS
    ấn
    1.38
    ướ
    1.23
    atasaray
    1.18
    űt
    1.18
    ⢸
    1.17
     menyampaikan
    1.17
    zey
    1.14
    ượu
    1.13
    atanga
    1.13
    adayo
    1.13
    Activations Density 0.093%

    No Known Activations