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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5861
    Prev
    Next
    INDEX
    Explanations

    common terms and phrases

    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_16k_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
     будь
    0.64
     عكس
    0.63
     е
    0.59
    数据的
    0.59
    يع
    0.57
     полноцен
    0.57
    說明
    0.55
     в
    0.54
     تكون
    0.54
     إ
    0.53
    POSITIVE LOGITS
     common
    1.23
    common
    1.09
    Common
    1.05
     Common
    1.05
    alities
    1.03
     COMMON
    0.96
     comunes
    0.93
     comum
    0.91
     comuni
    0.89
    ality
    0.86
    Activations Density 0.115%

    No Known Activations