© 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. 104105
    Prev
    Next
    INDEX
    Explanations

    Balkan Peninsula

    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
    ל
    0.57
     alternator
    0.52
     anta
    0.52
     инстру
    0.51
     formulate
    0.51
     piezo
    0.51
    م
    0.50
    תה
    0.50
     anten
    0.49
     calend
    0.49
    POSITIVE LOGITS
     schwierig
    0.50
    Mystery
    0.49
     Mystery
    0.48
     Wetlands
    0.48
     দেখলাম
    0.45
    dinger
    0.45
     kijk
    0.44
    Recommended
    0.44
    超過
    0.44
     möglicherweise
    0.44
    Activations Density 0.000%

    No Known Activations