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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 56804
    Prev
    Next
    INDEX
    Explanations

    based onbeyond the

    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_65k_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
     произ
    0.44
    ค์
    0.42
     коне
    0.42
     запя
    0.42
     ferns
    0.41
     факти
    0.40
     му
    0.39
    沣
    0.38
     despe
    0.38
     unei
    0.38
    POSITIVE LOGITS
    ۲
    0.51
    mc
    0.50
    ib
    0.47
    Chicago
    0.47
    ichi
    0.46
    ounds
    0.46
    izhou
    0.46
    ography
    0.45
    env
    0.45
    कोलॉजी
    0.45
    Activations Density 0.013%

    No Known Activations