© 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. 27026
    Prev
    Next
    INDEX
    Explanations

    follow instructions or calls to action

    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
    ا
    1.15
    า
    1.08
    手
    1.03
    大
    0.97
    ラ
    0.95
    mp
    0.91
     folgende
    0.90
    来说
    0.89
    一個
    0.88
    िन
    0.87
    POSITIVE LOGITS
    ות
    1.34
    ’
    1.17
    iw
    1.01
     coerced
    0.95
     minions
    0.94
    dır
    0.93
    ed
    0.91
    iers
    0.91
     Maver
    0.91
    th
    0.90
    Activations Density 0.006%

    No Known Activations