© 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. 31-GEMMASCOPE-2-RES-262K
    7. 48637
    Prev
    Next
    INDEX
    Explanations

    choices or instructions

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     dibujo
    0.47
    骄
    0.46
    ݢ
    0.46
     frio
    0.45
    ífico
    0.45
     feliz
    0.43
    serviceTime
    0.43
    MARINE
    0.43
     Pacífico
    0.43
    েন্ত্র
    0.43
    POSITIVE LOGITS
     или
    0.52
    或
    0.52
    ↵↵
    0.51
     or
    0.51
     harmful
    0.50
     such
    0.49
    或者
    0.48
    a
    0.48
     -
    0.48
     born
    0.46
    Activations Density 0.002%

    No Known Activations