© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 178342
    Prev
    Next
    INDEX
    Explanations

    business, performance, property, subway

    np_acts-logits-general · gemini-2.5-flash-lite

    than some, does with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    UpperCase
    0.43
    ibre
    0.42
     შ
    0.42
     ಮಾತ
    0.42
     ressembl
    0.42
     ventilation
    0.41
     quia
    0.41
     litre
    0.41
     이유
    0.41
     نگاه
    0.41
    POSITIVE LOGITS
    𝘢
    0.48
    wast
    0.46
     ठर
    0.45
    американ
    0.45
    ాలతో
    0.44
    ीय
    0.44
     inadequate
    0.44
    களை
    0.44
     определяет
    0.44
    𝐚
    0.44
    Activations Density 0.001%

    No Known Activations