© 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. 85641
    Prev
    Next
    INDEX
    Explanations

    breast milk and reviews

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

    Lux, Luxor, Gold, Silver

    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
    ONENTS
    0.49
     distorted
    0.47
     depositors
    0.46
     একান্ত
    0.46
     instants
    0.46
    uk
    0.45
    աստ
    0.45
     Elektrokh
    0.44
    ᱗
    0.44
    uestos
    0.43
    POSITIVE LOGITS
    Lux
    0.55
     Lux
    0.53
    르
    0.50
     Gold
    0.50
     Vaux
    0.50
     D
    0.50
     GTX
    0.49
     కి
    0.49
    e
    0.48
     Luxor
    0.48
    Activations Density 0.000%

    No Known Activations