© 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. 31-GEMMASCOPE-2-RES-262K
    7. 125792
    Prev
    Next
    INDEX
    Explanations

    history or their potential

    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_31_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
    这意味着
    0.48
    น้อย
    0.39
     inspe
    0.37
    节省
    0.36
     ponownie
    0.36
     pokuš
    0.36
    钝
    0.36
     inutil
    0.36
    权
    0.36
     projek
    0.35
    POSITIVE LOGITS
    CELL
    0.47
    רה
    0.47
    urethane
    0.45
     ಸಂತ
    0.44
    Foods
    0.43
    TING
    0.43
    
    0.43
    ohms
    0.43
    ABLE
    0.42
    comend
    0.42
    Activations Density 0.002%

    No Known Activations