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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 16896
    Prev
    Next
    INDEX
    Explanations

    secretary, corporate secretary, secretary general

    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_16_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
    '
    1.09
    ン
    1.07
     is
    0.99
    ك
    0.94
    ন
    0.92
    н
    0.92
    ن
    0.92
    ם
    0.91
    น
    0.89
    ینگ
    0.89
    POSITIVE LOGITS
    W
    1.29
    V
    1.22
    B
    1.21
    not
    1.16
    K
    1.11
    U
    1.08
    secretary
    1.07
    dropped
    1.05
    T
    1.05
     secretary
    1.03
    Activations Density 0.001%

    No Known Activations