© 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. 192474
    Prev
    Next
    INDEX
    Explanations

    transactional or operational terms

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

    financial and travel documents

    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
    ay
    0.51
    brightness
    0.49
    IOT
    0.48
    𝗜
    0.47
    IVA
    0.46
    IMENT
    0.46
    IME
    0.46
    ARE
    0.45
     polarity
    0.45
     つ
    0.45
    POSITIVE LOGITS
     Neue
    0.47
     Deniz
    0.44
     Basilica
    0.43
     Sheikh
    0.42
     Tidak
    0.42
    公司的
    0.41
     Sakura
    0.41
     Basil
    0.41
     Dmitry
    0.41
     Almanya
    0.41
    Activations Density 0.002%

    No Known Activations