© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 10814
    Prev
    Next
    INDEX
    Explanations

    save or rescue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ب
    1.88
    既然
    1.66
    t
    1.58
    ﻖ
    1.55
     hablamos
    1.54
    ﻂ
    1.54
    ﮏ
    1.52
     pianos
    1.51
     estaremos
    1.48
     aisles
    1.47
    POSITIVE LOGITS
    Rescue
    1.54
    ü
    1.54
    saves
    1.44
    救
    1.39
    Esp
    1.34
     rescue
    1.32
    İ
    1.32
    Ev
    1.31
    espa
    1.30
     نجات
    1.28
    Activations Density 0.132%

    No Known Activations