© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 4482
    Prev
    Next
    INDEX
    Explanations

    dictionary mapping

    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_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    cigarettes
    0.43
    Kuota
    0.39
     continuité
    0.38
     رقم
    0.38
    ळक
    0.38
     limbs
    0.38
    Liam
    0.38
    জিওথেরাপি
    0.37
     تصل
    0.37
     "*");
    0.37
    POSITIVE LOGITS
     dictionary
    2.06
     Dictionary
    1.92
     dict
    1.91
    字典
    1.84
    dict
    1.83
     dictionaries
    1.83
    Dictionary
    1.78
    dictionary
    1.78
     Dict
    1.75
    Dict
    1.74
    Activations Density 0.340%

    No Known Activations