© 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. 9106
    Prev
    Next
    INDEX
    Explanations

    at once

    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
    م
    3.03
    ل
    2.66
    ו
    2.53
    т
    2.50
    ු
    2.32
     也
    2.29
    м
    2.27
     哦
    2.27
     ‍
    2.27
     ငါ
    2.26
    POSITIVE LOGITS
    Š
    2.49
    Ď
    2.46
    Question
    2.44
    E
    2.39
    H
    2.39
    Zw
    2.34
    Nk
    2.34
    élément
    2.33
    Os
    2.32
    Accessibility
    2.29
    Activations Density 0.037%

    No Known Activations