© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 195715
    Prev
    Next
    INDEX
    Explanations

    plt.scatter size argument

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ッキリ
    0.42
    isyon
    0.39
    ンプ
    0.39
    鋼
    0.37
    ytu
    0.37
    aporte
    0.37
    elp
    0.37
    oyang
    0.36
    captivity
    0.35
    小型
    0.35
    POSITIVE LOGITS
    scrollHeight
    0.45
    视
    0.40
    typing
    0.39
     Sé
    0.39
     vé
    0.38
    ChildScrollView
    0.38
     AUR
    0.38
    сро
    0.37
     İm
    0.36
     Reaper
    0.36
    Activations Density 0.000%

    No Known Activations