© 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. 20784
    Prev
    Next
    INDEX
    Explanations

    jurisdictional laws and regulations

    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
    𝒃
    0.46
    𝑏
    0.43
    ÓN
    0.41
    Nx
    0.41
    bj
    0.40
    Kell
    0.39
    忍
    0.39
    ități
    0.39
    ექტ
    0.39
    ᾖ
    0.39
    POSITIVE LOGITS
     मान्यता
    0.53
     and
    0.46
     و
    0.45
     affiliate
    0.44
     recognised
    0.43
     Benedict
    0.43
     reconocido
    0.42
    عة
    0.42
     recognizes
    0.41
     recognition
    0.41
    Activations Density 0.004%

    No Known Activations