© 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. 110072
    Prev
    Next
    INDEX
    Explanations

    speak for itself

    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
     for
    0.61
     angry
    0.52
    </sup>
    0.50
     obce
    0.49
    //
    0.47
     angered
    0.47
     injured
    0.46
     wronged
    0.46
    I
    0.46
    Day
    0.46
    POSITIVE LOGITS
     내
    0.58
     কাজ
    0.57
     manej
    0.56
     создавать
    0.55
     کار
    0.55
     取り
    0.53
     결과를
    0.52
     ውጤ
    0.52
     работе
    0.52
     경쟁
    0.52
    Activations Density 0.002%

    No Known Activations